openapi: 3.0.3
paths:
  /v2/upload:
    post:
      operationId: FileController_upload_v2
      parameters: []
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                audio:
                  type: string
                  format: binary
                  description: The file to be uploaded. This should be an audio or video file.
          application/json:
            schema:
              type: object
              properties:
                audio_url:
                  type: string
                  description: The URL of the audio or video file to be uploaded.
      responses:
        '200':
          description: ''
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AudioUploadResponse'
      security:
      - x_gladia_key: []
      summary: Upload an audio file or provide an audio URL for processing
      tags:
      - File Management
  /v2/pre-recorded:
    post:
      operationId: PreRecordedController_initPreRecordedJob_v2
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/InitTranscriptionRequest'
      responses:
        '201':
          description: The pre recorded job has been initiated
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitPreRecordedTranscriptionResponse'
        '400':
          description: Something is wrong with the request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestErrorResponse'
        '401':
          description: You don't have the permissions to initiate a new pre recorded job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '422':
          description: The parameters you gave are incorrect
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnprocessableEntityErrorResponse'
      security:
      - x_gladia_key: []
      summary: Initiate a new pre recorded job
      tags:
      - Pre-recorded V2
    get:
      operationId: PreRecordedController_getPreRecordedJobs_v2
      parameters:
      - name: offset
        required: false
        in: query
        description: The starting point for pagination. A value of 0 starts from the first item.
        schema:
          minimum: 0
          default: 0
          type: integer
      - name: limit
        required: false
        in: query
        description: The maximum number of items to return. Useful for pagination and controlling data payload size.
        schema:
          minimum: 1
          default: 20
          type: integer
      - name: date
        required: false
        in: query
        description: Filter items relevant to a specific date in ISO format (YYYY-MM-DD).
        schema:
          format: date-time
          example: '2026-06-12'
          type: string
      - name: before_date
        required: false
        in: query
        description: Include items that occurred before the specified date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: after_date
        required: false
        in: query
        description: Filter for items after the specified date. Use with `before_date` for a range. Date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: status
        required: false
        in: query
        description: Filter the list based on item status. Accepts multiple values from the predefined list.
        schema:
          example:
          - done
          type: array
          items:
            type: string
            enum:
            - queued
            - processing
            - done
            - error
      - name: custom_metadata
        required: false
        in: query
        schema:
          additionalProperties: true
          example:
            user: John Doe
          type: object
      responses:
        '200':
          description: A list of pre recorded jobs matching the parameters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListPreRecordedResponse'
        '401':
          description: You don't have the permissions to access pre recorded jobs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
      security:
      - x_gladia_key: []
      summary: Get pre recorded jobs based on query parameters
      tags:
      - Pre-recorded V2
  /v2/pre-recorded/{id}:
    get:
      operationId: PreRecordedController_getPreRecordedJob_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the pre recorded job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '200':
          description: The pre recorded job's metadata
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PreRecordedResponse'
        '401':
          description: You don't have the permissions to access the pre recorded job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The pre recorded job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Get the pre recorded job's metadata
      tags:
      - Pre-recorded V2
    delete:
      operationId: PreRecordedController_deletePreRecordedJob_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the pre recorded job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '202':
          description: The pre recorded job has been successfully deleted
        '401':
          description: You don't have the permissions to delete this pre recorded job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '403':
          description: The pre recorded job is not in a deletable state
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ForbiddenErrorResponse'
        '404':
          description: The pre recorded job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Delete the pre recorded job
      tags:
      - Pre-recorded V2
  /v2/pre-recorded/{id}/file:
    get:
      operationId: PreRecordedController_getAudio_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the pre recorded job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '200':
          description: The audio file used for this pre recorded job
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                example: <binary>
        '401':
          description: You don't have the permissions to access this pre recorded job or its audio file
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The pre recorded job or its audio file doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Download the audio file used for this pre recorded job
      tags:
      - Pre-recorded V2
  /v2/transcription:
    post:
      operationId: TranscriptionController_initPreRecordedJob_v2
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/InitTranscriptionRequest'
      responses:
        '201':
          description: The transcription job has been initiated
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitPreRecordedTranscriptionResponse'
        '400':
          description: Something is wrong with the request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestErrorResponse'
        '401':
          description: You don't have the permissions to initiate a new transcription job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '422':
          description: The parameters you gave are incorrect
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnprocessableEntityErrorResponse'
      security:
      - x_gladia_key: []
      summary: Initiate a new transcription job
      tags:
      - Transcription V2
    get:
      operationId: TranscriptionController_list_v2
      parameters:
      - name: offset
        required: false
        in: query
        description: The starting point for pagination. A value of 0 starts from the first item.
        schema:
          minimum: 0
          default: 0
          type: integer
      - name: limit
        required: false
        in: query
        description: The maximum number of items to return. Useful for pagination and controlling data payload size.
        schema:
          minimum: 1
          default: 20
          type: integer
      - name: date
        required: false
        in: query
        description: Filter items relevant to a specific date in ISO format (YYYY-MM-DD).
        schema:
          format: date-time
          example: '2026-06-12'
          type: string
      - name: before_date
        required: false
        in: query
        description: Include items that occurred before the specified date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: after_date
        required: false
        in: query
        description: Filter for items after the specified date. Use with `before_date` for a range. Date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: status
        required: false
        in: query
        description: Filter the list based on item status. Accepts multiple values from the predefined list.
        schema:
          example:
          - done
          type: array
          items:
            type: string
            enum:
            - queued
            - processing
            - done
            - error
      - name: custom_metadata
        required: false
        in: query
        schema:
          additionalProperties: true
          example:
            user: John Doe
          type: object
      - name: kind
        required: false
        in: query
        description: Filter the list based on the item type. Supports multiple values from the predefined list.
        schema:
          example:
          - pre-recorded
          type: array
          items:
            type: string
            enum:
            - pre-recorded
            - live
      responses:
        '200':
          description: A list of transcription jobs matching the parameters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListTranscriptionResponse'
        '401':
          description: You don't have the permissions to access transcription jobs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
      security:
      - x_gladia_key: []
      summary: Get transcription jobs based on query parameters
      tags:
      - Transcription V2
  /v2/transcription/{id}:
    get:
      operationId: TranscriptionController_getTranscript_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the transcription job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '200':
          description: The transcription job's metadata
          content:
            application/json:
              schema:
                example:
                  id: 45463597-20b7-4af7-b3b3-f5fb778203ab
                  request_id: G-45463597
                  version: 2
                  kind: pre-recorded
                  created_at: '2023-12-28T09:04:17.210Z'
                  status: queued
                  file:
                    id: f0dcZE10-23d8-47f0-a25d-74a6eed88721
                    filename: split_infinity.wav
                    source: http://files.gladia.io/example/audio-transcription/split_infinity.wav
                    audio_duration: 20
                    number_of_channels: 1
                  request_params:
                    audio_url: http://files.gladia.io/example/audio-transcription/split_infinity.wav
                    subtitles: false
                    diarization: false
                    translation: false
                    summarization: false
                    sentences: false
                    moderation: false
                    named_entity_recognition: false
                    name_consistency: false
                    custom_spelling: false
                    structured_data_extraction: false
                    chapterization: false
                    sentiment_analysis: false
                    display_mode: false
                    audio_enhancer: false
                    language_config:
                      code_switching: false
                      languages:
                      - fr
                      - en
                    accurate_words_timestamps: false
                    diarization_enhanced: false
                    punctuation_enhanced: false
                  completed_at: null
                  custom_metadata: null
                  error_code: null
                  result: null
                oneOf:
                - $ref: '#/components/schemas/PreRecordedResponse'
                - $ref: '#/components/schemas/StreamingResponse'
                discriminator:
                  propertyName: kind
                  mapping:
                    pre-recorded: '#/components/schemas/PreRecordedResponse'
                    live: '#/components/schemas/StreamingResponse'
        '401':
          description: You don't have the permissions to access the transcription job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The transcription job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Get the transcription job's metadata
      tags:
      - Transcription V2
    delete:
      operationId: TranscriptionController_deleteTranscript_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the transcription job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '202':
          description: The transcription job has been successfully deleted
        '401':
          description: You don't have the permissions to delete this transcription job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '403':
          description: The transcription job is not in a deletable state
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ForbiddenErrorResponse'
        '404':
          description: The transcription job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Delete the transcription job
      tags:
      - Transcription V2
  /v2/transcription/{id}/file:
    get:
      operationId: TranscriptionController_getAudio_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the transcription job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '200':
          description: The audio file used for this transcription job
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                example: <binary>
        '401':
          description: You don't have the permissions to access this transcription job or its audio file
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The transcription job or its audio file doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Download the audio file used for this transcription job
      tags:
      - Transcription V2
  /audio/text/audio-transcription:
    post:
      operationId: AudioToTextController_audioTranscription
      parameters: []
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                audio:
                  type: string
                  format: binary
                audio_url:
                  type: string
                  default: http://files.gladia.io/example/audio-transcription/split_infinity.wav
                language_behaviour:
                  type: string
                  enum:
                  - automatic single language
                  - automatic multiple languages
                  - manual
                  default: automatic single language
                language:
                  type: string
                  enum:
                  - afrikaans
                  - albanian
                  - amharic
                  - arabic
                  - armenian
                  - assamese
                  - azerbaijani
                  - bashkir
                  - basque
                  - belarusian
                  - bengali
                  - bosnian
                  - breton
                  - bulgarian
                  - catalan
                  - chinese
                  - croatian
                  - czech
                  - danish
                  - dutch
                  - english
                  - estonian
                  - faroese
                  - finnish
                  - french
                  - galician
                  - georgian
                  - german
                  - greek
                  - gujarati
                  - haitian creole
                  - hausa
                  - hawaiian
                  - hebrew
                  - hindi
                  - hungarian
                  - icelandic
                  - indonesian
                  - italian
                  - japanese
                  - javanese
                  - kannada
                  - kazakh
                  - khmer
                  - korean
                  - lao
                  - latin
                  - latvian
                  - lingala
                  - lithuanian
                  - luxembourgish
                  - macedonian
                  - malagasy
                  - malay
                  - malayalam
                  - maltese
                  - maori
                  - marathi
                  - mongolian
                  - myanmar
                  - nepali
                  - norwegian
                  - nynorsk
                  - occitan
                  - pashto
                  - persian
                  - polish
                  - portuguese
                  - punjabi
                  - romanian
                  - russian
                  - sanskrit
                  - serbian
                  - shona
                  - sindhi
                  - sinhala
                  - slovak
                  - slovenian
                  - somali
                  - spanish
                  - sundanese
                  - swahili
                  - swedish
                  - tagalog
                  - tajik
                  - tamil
                  - tatar
                  - telugu
                  - thai
                  - tibetan
                  - turkish
                  - turkmen
                  - ukrainian
                  - urdu
                  - uzbek
                  - vietnamese
                  - welsh
                  - yiddish
                  - yoruba
                transcription_hint:
                  type: string
                toggle_diarization:
                  type: boolean
                  default: false
                diarization_num_speakers:
                  type: integer
                diarization_min_speakers:
                  type: integer
                diarization_max_speakers:
                  type: integer
                toggle_direct_translate:
                  type: boolean
                  default: false
                target_translation_language:
                  type: string
                  enum:
                  - afrikaans
                  - albanian
                  - amharic
                  - arabic
                  - armenian
                  - assamese
                  - azerbaijani
                  - bashkir
                  - basque
                  - belarusian
                  - bengali
                  - bosnian
                  - breton
                  - bulgarian
                  - catalan
                  - chinese
                  - croatian
                  - czech
                  - danish
                  - dutch
                  - english
                  - estonian
                  - faroese
                  - finnish
                  - french
                  - galician
                  - georgian
                  - german
                  - greek
                  - gujarati
                  - haitian creole
                  - hausa
                  - hawaiian
                  - hebrew
                  - hindi
                  - hungarian
                  - icelandic
                  - indonesian
                  - italian
                  - japanese
                  - javanese
                  - kannada
                  - kazakh
                  - khmer
                  - korean
                  - lao
                  - latin
                  - latvian
                  - lingala
                  - lithuanian
                  - luxembourgish
                  - macedonian
                  - malagasy
                  - malay
                  - malayalam
                  - maltese
                  - maori
                  - marathi
                  - mongolian
                  - myanmar
                  - nepali
                  - norwegian
                  - nynorsk
                  - occitan
                  - pashto
                  - persian
                  - polish
                  - portuguese
                  - punjabi
                  - romanian
                  - russian
                  - sanskrit
                  - serbian
                  - shona
                  - sindhi
                  - sinhala
                  - slovak
                  - slovenian
                  - somali
                  - spanish
                  - sundanese
                  - swahili
                  - swedish
                  - tagalog
                  - tajik
                  - tamil
                  - tatar
                  - telugu
                  - thai
                  - tibetan
                  - turkish
                  - turkmen
                  - ukrainian
                  - urdu
                  - uzbek
                  - vietnamese
                  - welsh
                  - wolof
                  - yiddish
                  - yoruba
                output_format:
                  type: string
                  enum:
                  - json
                  - srt
                  - vtt
                  - plain
                  - txt
                  default: json
                toggle_noise_reduction:
                  type: boolean
                  default: false
                toggle_accurate_words_timestamps:
                  type: boolean
                  default: false
                webhook_url:
                  type: string
      responses:
        '200':
          description: ''
      security:
      - x_gladia_key: []
      tags:
      - AudioToText
      - Transcription V1
  /video/text/video-transcription:
    post:
      operationId: VideoToTextController_videoTranscription
      parameters: []
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                video:
                  type: string
                  format: binary
                video_url:
                  type: string
                  default: http://files.gladia.io/example/audio-transcription/split_infinity.wav
                language_behaviour:
                  type: string
                  enum:
                  - automatic single language
                  - automatic multiple languages
                  - manual
                  default: automatic single language
                language:
                  type: string
                  enum:
                  - afrikaans
                  - albanian
                  - amharic
                  - arabic
                  - armenian
                  - assamese
                  - azerbaijani
                  - bashkir
                  - basque
                  - belarusian
                  - bengali
                  - bosnian
                  - breton
                  - bulgarian
                  - catalan
                  - chinese
                  - croatian
                  - czech
                  - danish
                  - dutch
                  - english
                  - estonian
                  - faroese
                  - finnish
                  - french
                  - galician
                  - georgian
                  - german
                  - greek
                  - gujarati
                  - haitian creole
                  - hausa
                  - hawaiian
                  - hebrew
                  - hindi
                  - hungarian
                  - icelandic
                  - indonesian
                  - italian
                  - japanese
                  - javanese
                  - kannada
                  - kazakh
                  - khmer
                  - korean
                  - lao
                  - latin
                  - latvian
                  - lingala
                  - lithuanian
                  - luxembourgish
                  - macedonian
                  - malagasy
                  - malay
                  - malayalam
                  - maltese
                  - maori
                  - marathi
                  - mongolian
                  - myanmar
                  - nepali
                  - norwegian
                  - nynorsk
                  - occitan
                  - pashto
                  - persian
                  - polish
                  - portuguese
                  - punjabi
                  - romanian
                  - russian
                  - sanskrit
                  - serbian
                  - shona
                  - sindhi
                  - sinhala
                  - slovak
                  - slovenian
                  - somali
                  - spanish
                  - sundanese
                  - swahili
                  - swedish
                  - tagalog
                  - tajik
                  - tamil
                  - tatar
                  - telugu
                  - thai
                  - tibetan
                  - turkish
                  - turkmen
                  - ukrainian
                  - urdu
                  - uzbek
                  - vietnamese
                  - welsh
                  - yiddish
                  - yoruba
                transcription_hint:
                  type: string
                toggle_diarization:
                  type: boolean
                  default: false
                diarization_num_speakers:
                  type: integer
                diarization_min_speakers:
                  type: integer
                diarization_max_speakers:
                  type: integer
                toggle_direct_translate:
                  type: boolean
                  default: false
                target_translation_language:
                  type: string
                  enum:
                  - afrikaans
                  - albanian
                  - amharic
                  - arabic
                  - armenian
                  - assamese
                  - azerbaijani
                  - bashkir
                  - basque
                  - belarusian
                  - bengali
                  - bosnian
                  - breton
                  - bulgarian
                  - catalan
                  - chinese
                  - croatian
                  - czech
                  - danish
                  - dutch
                  - english
                  - estonian
                  - faroese
                  - finnish
                  - french
                  - galician
                  - georgian
                  - german
                  - greek
                  - gujarati
                  - haitian creole
                  - hausa
                  - hawaiian
                  - hebrew
                  - hindi
                  - hungarian
                  - icelandic
                  - indonesian
                  - italian
                  - japanese
                  - javanese
                  - kannada
                  - kazakh
                  - khmer
                  - korean
                  - lao
                  - latin
                  - latvian
                  - lingala
                  - lithuanian
                  - luxembourgish
                  - macedonian
                  - malagasy
                  - malay
                  - malayalam
                  - maltese
                  - maori
                  - marathi
                  - mongolian
                  - myanmar
                  - nepali
                  - norwegian
                  - nynorsk
                  - occitan
                  - pashto
                  - persian
                  - polish
                  - portuguese
                  - punjabi
                  - romanian
                  - russian
                  - sanskrit
                  - serbian
                  - shona
                  - sindhi
                  - sinhala
                  - slovak
                  - slovenian
                  - somali
                  - spanish
                  - sundanese
                  - swahili
                  - swedish
                  - tagalog
                  - tajik
                  - tamil
                  - tatar
                  - telugu
                  - thai
                  - tibetan
                  - turkish
                  - turkmen
                  - ukrainian
                  - urdu
                  - uzbek
                  - vietnamese
                  - welsh
                  - wolof
                  - yiddish
                  - yoruba
                output_format:
                  type: string
                  enum:
                  - json
                  - srt
                  - vtt
                  - plain
                  - txt
                  default: json
                toggle_noise_reduction:
                  type: boolean
                  default: false
                toggle_accurate_words_timestamps:
                  type: boolean
                  default: false
                webhook_url:
                  type: string
      responses:
        '200':
          description: ''
      security:
      - x_gladia_key: []
      tags:
      - Transcription V1
  /v1/history:
    get:
      operationId: HistoryController_getList_v1
      parameters:
      - name: offset
        required: false
        in: query
        description: The starting point for pagination. A value of 0 starts from the first item.
        schema:
          minimum: 0
          default: 0
          type: integer
      - name: limit
        required: false
        in: query
        description: The maximum number of items to return. Useful for pagination and controlling data payload size.
        schema:
          minimum: 1
          default: 20
          type: integer
      - name: date
        required: false
        in: query
        description: Filter items relevant to a specific date in ISO format (YYYY-MM-DD).
        schema:
          format: date-time
          example: '2026-06-12'
          type: string
      - name: before_date
        required: false
        in: query
        description: Include items that occurred before the specified date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: after_date
        required: false
        in: query
        description: Filter for items after the specified date. Use with `before_date` for a range. Date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: status
        required: false
        in: query
        description: Filter the list based on item status. Accepts multiple values from the predefined list.
        schema:
          example:
          - done
          type: array
          items:
            type: string
            enum:
            - queued
            - processing
            - done
            - error
      - name: custom_metadata
        required: false
        in: query
        schema:
          additionalProperties: true
          example:
            user: John Doe
          type: object
      - name: kind
        required: false
        in: query
        description: Filter the list based on the item type. Supports multiple values from the predefined list.
        schema:
          example:
          - pre-recorded
          type: array
          items:
            type: string
            enum:
            - pre-recorded
            - live
      responses:
        '200':
          description: A list of jobs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListHistoryResponse'
      security:
      - x_gladia_key: []
      summary: Get the history of all your jobs
      tags:
      - Job History
  /v2/live:
    post:
      operationId: StreamingController_initStreamingSession_v2
      parameters:
      - name: region
        required: false
        in: query
        description: The region used to process the audio.
        schema:
          $ref: '#/components/schemas/StreamingSupportedRegions'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/StreamingRequest'
      responses:
        '201':
          description: The live job has been initiated
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitStreamingResponse'
        '400':
          description: Something is wrong with the request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestErrorResponse'
        '401':
          description: You don't have the permissions to initiate a new live job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '422':
          description: The parameters you gave are incorrect
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnprocessableEntityErrorResponse'
      security:
      - x_gladia_key: []
      summary: Initiate a new live job
      tags:
      - Live V2
    get:
      operationId: StreamingController_getStreamingJobs_v2
      parameters:
      - name: offset
        required: false
        in: query
        description: The starting point for pagination. A value of 0 starts from the first item.
        schema:
          minimum: 0
          default: 0
          type: integer
      - name: limit
        required: false
        in: query
        description: The maximum number of items to return. Useful for pagination and controlling data payload size.
        schema:
          minimum: 1
          default: 20
          type: integer
      - name: date
        required: false
        in: query
        description: Filter items relevant to a specific date in ISO format (YYYY-MM-DD).
        schema:
          format: date-time
          example: '2026-06-12'
          type: string
      - name: before_date
        required: false
        in: query
        description: Include items that occurred before the specified date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: after_date
        required: false
        in: query
        description: Filter for items after the specified date. Use with `before_date` for a range. Date in ISO format.
        schema:
          format: date-time
          example: '2026-06-12T21:00:09.947Z'
          type: string
      - name: status
        required: false
        in: query
        description: Filter the list based on item status. Accepts multiple values from the predefined list.
        schema:
          example:
          - done
          type: array
          items:
            type: string
            enum:
            - queued
            - processing
            - done
            - error
      - name: custom_metadata
        required: false
        in: query
        schema:
          additionalProperties: true
          example:
            user: John Doe
          type: object
      responses:
        '200':
          description: A list of live jobs matching the parameters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListStreamingResponse'
        '401':
          description: You don't have the permissions to access live jobs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
      security:
      - x_gladia_key: []
      summary: Get live jobs based on query parameters
      tags:
      - Live V2
  /v2/live/{id}:
    get:
      operationId: StreamingController_getStreamingJob_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the live job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '200':
          description: The live job's metadata
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StreamingResponse'
        '401':
          description: You don't have the permissions to access the live job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The live job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Get the live job's metadata
      tags:
      - Live V2
    delete:
      operationId: StreamingController_deleteStreamingJob_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the live job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '202':
          description: The live job has been successfully deleted
        '401':
          description: You don't have the permissions to delete this live job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '403':
          description: The live job is not in a deletable state
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ForbiddenErrorResponse'
        '404':
          description: The live job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Delete the live job
      tags:
      - Live V2
    patch:
      operationId: StreamingController_patchRequestParams_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the live job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PatchRequestParamsDTO'
      responses:
        '204':
          description: Successfully patched the job
        '400':
          description: Something is wrong with the request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequestErrorResponse'
        '401':
          description: You don't have the permissions to update the job
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The live job doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
        '413':
          description: The post_request_metadata parameter must be a json object no longer that 100kb
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PayloadTooLargeErrorResponse'
      security:
      - x_gladia_key: []
      summary: For debugging purposes, send post session metadata in the request params of the job
      tags:
      - Live V2
  /v2/live/{id}/file:
    get:
      operationId: StreamingController_getAudio_v2
      parameters:
      - name: id
        required: true
        in: path
        description: Id of the live job
        schema:
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
          type: string
      responses:
        '200':
          description: The audio file used for this live job
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                example: <binary>
        '401':
          description: You don't have the permissions to access this live job or its audio file
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedErrorResponse'
        '404':
          description: The live job or its audio file doesn't exist or has been deleted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundErrorResponse'
      security:
      - x_gladia_key: []
      summary: Download the audio file used for this live job
      tags:
      - Live V2
  /v1/models:
    get:
      operationId: ModelsController_list_v1
      parameters: []
      responses:
        '200':
          description: List of available models
      summary: List Gladia's available transcription models as per OpenRouter integration spec
      tags:
      - OpenRouter
info:
  title: Gladia Control API
  description: Gladia AI audio infrastructure API for speech-to-text transcription via REST and WebSocket. Supports asynchronous
    pre-recorded audio processing and real-time live transcription with speaker diarization, automatic language detection
    across 100+ languages, and audio intelligence features.
  version: '1.0'
  contact: {}
tags: []
servers:
- url: https://api.gladia.io/
  description: Gladia API production URL
components:
  securitySchemes:
    x_gladia_key:
      type: apiKey
      in: header
      name: x-gladia-key
      description: Your personal Gladia API key
  schemas:
    PreRecordedEventPayload:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
      required:
      - id
    LiveEventPayload:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
      required:
      - id
    UploadBody:
      type: object
      properties: {}
    AudioUploadMetadataDTO:
      type: object
      properties:
        id:
          type: string
          description: Uploaded audio file ID
          format: uuid
          example: 6c09400e-23d2-4bd2-be55-96a5ececfa3b
        filename:
          type: string
          description: Uploaded audio filename
          example: short-audio-en-16000.wav
        source:
          type: string
          description: Uploaded audio source
          format: uri
          example: http://files.gladia.io/example/audio-transcription/split_infinity.wav
        extension:
          type: string
          description: Uploaded audio detected extension
          format: uuid
          example: wav
        size:
          type: integer
          description: Uploaded audio size
          example: 365702
        audio_duration:
          type: number
          description: Uploaded audio duration
          example: 4.145782
        number_of_channels:
          type: integer
          description: Uploaded audio channel numbers
          example: 1
      required:
      - id
      - filename
      - extension
      - size
      - audio_duration
      - number_of_channels
    AudioUploadResponse:
      type: object
      properties:
        audio_url:
          type: string
          description: Uploaded audio file Gladia URL
          format: uri
          example: https://api.gladia.io/file/6c09400e-23d2-4bd2-be55-96a5ececfa3b
        audio_metadata:
          description: Uploaded audio file detected metadata
          allOf:
          - $ref: '#/components/schemas/AudioUploadMetadataDTO'
      required:
      - audio_url
      - audio_metadata
    TranscriptionLanguageCodeEnum:
      type: string
      enum:
      - af
      - am
      - ar
      - as
      - az
      - ba
      - be
      - bg
      - bn
      - bo
      - br
      - bs
      - ca
      - cs
      - cy
      - da
      - de
      - el
      - en
      - es
      - et
      - eu
      - fa
      - fi
      - fo
      - fr
      - gl
      - gu
      - ha
      - haw
      - he
      - hi
      - hr
      - ht
      - hu
      - hy
      - id
      - is
      - it
      - ja
      - jw
      - ka
      - kk
      - km
      - kn
      - ko
      - la
      - lb
      - ln
      - lo
      - lt
      - lv
      - mg
      - mi
      - mk
      - ml
      - mn
      - mr
      - ms
      - mt
      - my
      - ne
      - nl
      - nn
      - 'no'
      - oc
      - pa
      - pl
      - ps
      - pt
      - ro
      - ru
      - sa
      - sd
      - si
      - sk
      - sl
      - sn
      - so
      - sq
      - sr
      - su
      - sv
      - sw
      - ta
      - te
      - tg
      - th
      - tk
      - tl
      - tr
      - tt
      - uk
      - ur
      - uz
      - vi
      - yi
      - yo
      - zh
      description: Specify the language in which it will be pronounced when sound comparison occurs. Default to transcription
        language.
    CustomVocabularyEntryDTO:
      type: object
      properties:
        value:
          type: string
          description: The text used to replace in the transcription.
          example: Gladia
        intensity:
          type: number
          description: The global intensity of the feature.
          example: 0.5
          minimum: 0
          maximum: 1
        pronunciations:
          description: The pronunciations used in the transcription.
          type: array
          items:
            type: string
        language:
          description: Specify the language in which it will be pronounced when sound comparison occurs. Default to transcription
            language.
          example: en
          allOf:
          - $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
      required:
      - value
    CustomVocabularyConfigDTO:
      type: object
      properties:
        vocabulary:
          type: array
          description: 'Specific vocabulary list to feed the transcription model with. Each item can be a string or an object
            with the following properties: value, intensity, pronunciations, language.'
          example:
          - Westeros
          - value: Stark
          - value: Night's Watch
            pronunciations:
            - Nightz Watch
            intensity: 0.4
            language: en
          items:
            oneOf:
            - $ref: '#/components/schemas/CustomVocabularyEntryDTO'
            - type: string
        default_intensity:
          type: number
          description: Default intensity for the custom vocabulary
          example: 0.5
          minimum: 0
          maximum: 1
      required:
      - vocabulary
    CallbackMethodEnum:
      type: string
      enum:
      - POST
      - PUT
      description: 'The HTTP method to be used. Allowed values are `POST` or `PUT` (default: `POST`)'
    CallbackConfigDto:
      type: object
      properties:
        url:
          type: string
          description: The URL to be called with the result of the transcription
          example: http://callback.example
          format: uri
        method:
          description: 'The HTTP method to be used. Allowed values are `POST` or `PUT` (default: `POST`)'
          example: POST
          default: POST
          allOf:
          - $ref: '#/components/schemas/CallbackMethodEnum'
      required:
      - url
    SubtitlesFormatEnum:
      type: string
      enum:
      - srt
      - vtt
      description: Subtitles formats you want your transcription to be formatted to
    SubtitlesStyleEnum:
      type: string
      enum:
      - default
      - compliance
      description: 'Style of the subtitles. Compliance mode refers to : https://loc.gov/preservation/digital/formats//fdd/fdd000569.shtml#:~:text=SRT%20files%20are%20basic%20text,alongside%2C%20example%3A%20%22MyVideo123'
    SubtitlesConfigDTO:
      type: object
      properties:
        formats:
          type: array
          description: Subtitles formats you want your transcription to be formatted to
          default:
          - srt
          minItems: 1
          example:
          - srt
          items:
            $ref: '#/components/schemas/SubtitlesFormatEnum'
        minimum_duration:
          type: number
          description: Minimum duration of a subtitle in seconds
          minimum: 0
        maximum_duration:
          type: number
          description: Maximum duration of a subtitle in seconds
          minimum: 1
          maximum: 30
        maximum_characters_per_row:
          type: integer
          description: Maximum number of characters per row in a subtitle
          minimum: 1
        maximum_rows_per_caption:
          type: integer
          description: Maximum number of rows per caption
          minimum: 1
          maximum: 5
        style:
          description: 'Style of the subtitles. Compliance mode refers to : https://loc.gov/preservation/digital/formats//fdd/fdd000569.shtml#:~:text=SRT%20files%20are%20basic%20text,alongside%2C%20example%3A%20%22MyVideo123'
          default: default
          allOf:
          - $ref: '#/components/schemas/SubtitlesStyleEnum'
    DiarizationConfigDTO:
      type: object
      properties:
        number_of_speakers:
          type: integer
          description: Exact number of speakers in the audio
          example: 3
          minimum: 1
        min_speakers:
          type: integer
          description: Minimum number of speakers in the audio
          example: 1
          minimum: 0
        max_speakers:
          type: integer
          description: Maximum number of speakers in the audio
          example: 2
          minimum: 0
    TranslationLanguageCodeEnum:
      type: string
      enum:
      - af
      - am
      - ar
      - as
      - az
      - ba
      - be
      - bg
      - bn
      - bo
      - br
      - bs
      - ca
      - cs
      - cy
      - da
      - de
      - el
      - en
      - es
      - et
      - eu
      - fa
      - fi
      - fo
      - fr
      - gl
      - gu
      - ha
      - haw
      - he
      - hi
      - hr
      - ht
      - hu
      - hy
      - id
      - is
      - it
      - ja
      - jw
      - ka
      - kk
      - km
      - kn
      - ko
      - la
      - lb
      - ln
      - lo
      - lt
      - lv
      - mg
      - mi
      - mk
      - ml
      - mn
      - mr
      - ms
      - mt
      - my
      - ne
      - nl
      - nn
      - 'no'
      - oc
      - pa
      - pl
      - ps
      - pt
      - ro
      - ru
      - sa
      - sd
      - si
      - sk
      - sl
      - sn
      - so
      - sq
      - sr
      - su
      - sv
      - sw
      - ta
      - te
      - tg
      - th
      - tk
      - tl
      - tr
      - tt
      - uk
      - ur
      - uz
      - vi
      - wo
      - yi
      - yo
      - zh
      description: Target language in `iso639-1` format you want the transcription translated to
    TranslationModelEnum:
      type: string
      enum:
      - base
      - enhanced
      description: Model you want the translation model to use to translate
    TranslationConfigDTO:
      type: object
      properties:
        target_languages:
          type: array
          description: Target language in `iso639-1` format you want the transcription translated to
          example:
          - en
          minItems: 1
          items:
            $ref: '#/components/schemas/TranslationLanguageCodeEnum'
        model:
          description: Model you want the translation model to use to translate
          default: base
          allOf:
          - $ref: '#/components/schemas/TranslationModelEnum'
        match_original_utterances:
          type: boolean
          description: Align translated utterances with the original ones
          default: true
        lipsync:
          type: boolean
          description: 'Whether to apply lipsync to the translated transcription. '
          default: true
        context_adaptation:
          type: boolean
          description: Enables or disables context-aware translation features that allow the model to adapt translations based
            on provided context.
          default: true
        context:
          type: string
          description: Context information to improve translation accuracy
        informal:
          type: boolean
          description: Forces the translation to use informal language forms when available in the target language.
          default: false
      required:
      - target_languages
    SummaryTypesEnum:
      type: string
      enum:
      - general
      - bullet_points
      - concise
      description: The type of summarization to apply
    SummarizationConfigDTO:
      type: object
      properties:
        type:
          description: The type of summarization to apply
          default: general
          allOf:
          - $ref: '#/components/schemas/SummaryTypesEnum'
    CustomSpellingConfigDTO:
      type: object
      properties:
        spelling_dictionary:
          type: object
          description: The list of spelling applied on the audio transcription
          example:
            Gettleman:
            - gettleman
            SQL:
            - Sequel
          additionalProperties:
            type: array
            items:
              type: string
      required:
      - spelling_dictionary
    AudioToLlmListConfigDTO:
      type: object
      properties:
        prompts:
          description: The list of prompts applied on the audio transcription
          example:
          - Extract the key points from the transcription
          minItems: 1
          type: array
          items:
            type: array
        model:
          type: string
          description: The model to use for the prompt execution. You can find the list of supported models [here](https://openrouter.ai/models).
          default: openai/gpt-5.4-nano
      required:
      - prompts
    PiiRedactionEntityTypeEnum:
      type: string
      enum:
      - APPI
      - APPI_SENSITIVE
      - CCI
      - CORE_ENTITIES
      - CPRA
      - GDPR
      - GDPR_SENSITIVE
      - HEALTH_INFORMATION
      - HIPAA_SAFE_HARBOR
      - LIDI
      - NUMERICAL_EXCL_PCI
      - PCI
      - QUEBEC_PRIVACY_ACT
      - ACCOUNT_NUMBER
      - AGE
      - DATE
      - DATE_INTERVAL
      - DOB
      - DRIVER_LICENSE
      - DURATION
      - EMAIL_ADDRESS
      - EVENT
      - FILENAME
      - GENDER
      - HEALTHCARE_NUMBER
      - IP_ADDRESS
      - LANGUAGE
      - LOCATION
      - LOCATION_ADDRESS
      - LOCATION_ADDRESS_STREET
      - LOCATION_CITY
      - LOCATION_COORDINATE
      - LOCATION_COUNTRY
      - LOCATION_STATE
      - LOCATION_ZIP
      - MARITAL_STATUS
      - MONEY
      - NAME
      - NAME_FAMILY
      - NAME_GIVEN
      - NAME_MEDICAL_PROFESSIONAL
      - NUMERICAL_PII
      - OCCUPATION
      - ORGANIZATION
      - ORGANIZATION_MEDICAL_FACILITY
      - ORIGIN
      - PASSPORT_NUMBER
      - PASSWORD
      - PHONE_NUMBER
      - PHYSICAL_ATTRIBUTE
      - POLITICAL_AFFILIATION
      - RELIGION
      - SEXUALITY
      - SSN
      - TIME
      - URL
      - USERNAME
      - VEHICLE_ID
      - ZODIAC_SIGN
      - BLOOD_TYPE
      - CONDITION
      - DOSE
      - DRUG
      - INJURY
      - MEDICAL_PROCESS
      - STATISTICS
      - BANK_ACCOUNT
      - CREDIT_CARD
      - CREDIT_CARD_EXPIRATION
      - CVV
      - ROUTING_NUMBER
      - CORPORATE_ACTION
      - DAY
      - EFFECT
      - FINANCIAL_METRIC
      - MEDICAL_CODE
      - MONTH
      - ORGANIZATION_ID
      - PRODUCT
      - PROJECT
      - TREND
      - YEAR
      description: The entity types to redact
    PiiRedactionConfigDTO:
      type: object
      properties:
        entity_types:
          description: The entity types to redact
          example:
          - GDPR
          - HEALTH_INFORMATION
          - HIPAA_SAFE_HARBOR
          - QUEBEC_PRIVACY_ACT
          - EMAIL_ADDRESS
          - NAME
          - PHONE_NUMBER
          allOf:
          - $ref: '#/components/schemas/PiiRedactionEntityTypeEnum'
        processed_text_type:
          type: string
          description: The type of processed text to return (marker or mask)
          enum:
          - MARKER
          - MASK
          example: MARKER
    LanguageConfig:
      type: object
      properties:
        languages:
          type: array
          description: If one language is set, it will be used for the transcription. Otherwise, language will be auto-detected
            by the model.
          default: []
          items:
            $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
        code_switching:
          type: boolean
          description: If true, language will be auto-detected on each utterance. Otherwise, language will be auto-detected
            on first utterance and then used for the rest of the transcription. If one language is set, this option will be
            ignored.
          default: false
    InitTranscriptionRequest:
      type: object
      properties:
        custom_vocabulary:
          type: boolean
          description: '**[Beta]** Can be either boolean to enable custom_vocabulary for this audio or an array with specific
            vocabulary list to feed the transcription model with'
          default: false
        custom_vocabulary_config:
          description: '**[Beta]** Custom vocabulary configuration, if `custom_vocabulary` is enabled'
          allOf:
          - $ref: '#/components/schemas/CustomVocabularyConfigDTO'
        callback_url:
          type: string
          description: '**[Deprecated]** Use `callback`/`callback_config` instead. Callback URL we will do a `POST` request
            to with the result of the transcription'
          example: http://callback.example
          format: uri
          deprecated: true
        callback:
          type: boolean
          description: Enable callback for this transcription. If true, the `callback_config` property will be used to customize
            the callback behaviour
          default: false
        callback_config:
          description: Customize the callback behaviour (url and http method)
          allOf:
          - $ref: '#/components/schemas/CallbackConfigDto'
        subtitles:
          type: boolean
          description: Enable subtitles generation for this transcription
          default: false
        subtitles_config:
          description: Configuration for subtitles generation if `subtitles` is enabled
          allOf:
          - $ref: '#/components/schemas/SubtitlesConfigDTO'
        diarization:
          type: boolean
          description: Enable speaker recognition (diarization) for this audio
          default: false
        diarization_config:
          description: Speaker recognition configuration, if `diarization` is enabled
          allOf:
          - $ref: '#/components/schemas/DiarizationConfigDTO'
        translation:
          type: boolean
          description: '**[Beta]** Enable translation for this audio'
          default: false
        translation_config:
          description: '**[Beta]** Translation configuration, if `translation` is enabled'
          allOf:
          - $ref: '#/components/schemas/TranslationConfigDTO'
        summarization:
          type: boolean
          description: Enable summarization for this audio
          default: false
        summarization_config:
          description: Summarization configuration, if `summarization` is enabled
          allOf:
          - $ref: '#/components/schemas/SummarizationConfigDTO'
        named_entity_recognition:
          type: boolean
          description: '**[Alpha]** Enable named entity recognition for this audio'
          default: false
        custom_spelling:
          type: boolean
          description: '**[Alpha]** Enable custom spelling for this audio'
          default: false
        custom_spelling_config:
          description: '**[Alpha]** Custom spelling configuration, if `custom_spelling` is enabled'
          allOf:
          - $ref: '#/components/schemas/CustomSpellingConfigDTO'
        sentiment_analysis:
          type: boolean
          description: Enable sentiment analysis for this audio
          default: false
        audio_to_llm:
          type: boolean
          description: Enable audio to LLM processing for this audio
          default: false
        audio_to_llm_config:
          description: Audio to LLM configuration, if `audio_to_llm` is enabled
          allOf:
          - $ref: '#/components/schemas/AudioToLlmListConfigDTO'
        pii_redaction:
          type: boolean
          description: Enable PII redaction for this audio
          default: false
        pii_redaction_config:
          description: PII redaction configuration, if `pii_redaction` is enabled
          allOf:
          - $ref: '#/components/schemas/PiiRedactionConfigDTO'
        custom_metadata:
          type: object
          description: Custom metadata you can attach to this transcription
          example:
            user: John Doe
          additionalProperties: true
        sentences:
          type: boolean
          description: Enable sentences for this audio
          default: false
        punctuation_enhanced:
          type: boolean
          description: '**[Alpha]** Use enhanced punctuation for this audio'
          default: false
        language_config:
          description: Specify the language configuration
          allOf:
          - $ref: '#/components/schemas/LanguageConfig'
        audio_url:
          type: string
          description: URL to a Gladia file or to an external audio or video file
          example: http://files.gladia.io/example/audio-transcription/split_infinity.wav
          format: uri
      required:
      - audio_url
    InitPreRecordedTranscriptionResponse:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        result_url:
          type: string
          description: Prebuilt URL with your transcription `id` to fetch the result
          example: https://api.gladia.io/v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
          format: uri
      required:
      - id
      - result_url
    BadRequestErrorResponse:
      type: object
      properties:
        timestamp:
          type: string
          description: Date of when the error occurred
          example: '2023-12-28T09:04:17.210Z'
        path:
          type: string
          description: Path to the API endpoint
          example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-821fe9df
        statusCode:
          type: number
          description: HTTP status code of the error
          example: 400
        message:
          type: string
          description: Error message
          example: Content-Type is missing Multipart Boundary.
        validation_errors:
          description: List of validation errors, if any
          example:
          - Field "language" must be a string
          - Field "min_speakers" must be a number
          type: array
          items:
            type: string
      required:
      - timestamp
      - path
      - request_id
      - statusCode
      - message
    UnauthorizedErrorResponse:
      type: object
      properties:
        timestamp:
          type: string
          description: Date of when the error occurred
          example: '2023-12-28T09:04:17.210Z'
        path:
          type: string
          description: Path to the API endpoint
          example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-821fe9df
        statusCode:
          type: number
          description: HTTP status code of the error
          example: 401
        message:
          type: string
          description: Error message
          example: gladia key not found
      required:
      - timestamp
      - path
      - request_id
      - statusCode
      - message
    UnprocessableEntityErrorResponse:
      type: object
      properties:
        timestamp:
          type: string
          description: Date of when the error occurred
          example: '2023-12-28T09:04:17.210Z'
        path:
          type: string
          description: Path to the API endpoint
          example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-821fe9df
        statusCode:
          type: number
          description: HTTP status code of the error
          example: 422
        message:
          type: string
          description: Error message
          example: Invalid parameter
      required:
      - timestamp
      - path
      - request_id
      - statusCode
      - message
    FileResponse:
      type: object
      properties:
        id:
          type: string
          description: The file id
        filename:
          type: string
          nullable: true
          description: The name of the uploaded file
        source:
          type: string
          nullable: true
          description: The link used to download the file if audio_url was used
        audio_duration:
          type: number
          nullable: true
          description: Duration of the audio file
          example: 3600
        number_of_channels:
          type: integer
          nullable: true
          description: Number of channels in the audio file
          minimum: 1
          example: 1
      required:
      - id
      - filename
      - source
      - audio_duration
      - number_of_channels
    PreRecordedRequestParamsResponse:
      type: object
      properties:
        custom_vocabulary:
          type: boolean
          description: '**[Beta]** Can be either boolean to enable custom_vocabulary for this audio or an array with specific
            vocabulary list to feed the transcription model with'
          default: false
        custom_vocabulary_config:
          description: '**[Beta]** Custom vocabulary configuration, if `custom_vocabulary` is enabled'
          allOf:
          - $ref: '#/components/schemas/CustomVocabularyConfigDTO'
        callback_url:
          type: string
          description: '**[Deprecated]** Use `callback`/`callback_config` instead. Callback URL we will do a `POST` request
            to with the result of the transcription'
          example: http://callback.example
          format: uri
          deprecated: true
        callback:
          type: boolean
          description: Enable callback for this transcription. If true, the `callback_config` property will be used to customize
            the callback behaviour
          default: false
        callback_config:
          description: Customize the callback behaviour (url and http method)
          allOf:
          - $ref: '#/components/schemas/CallbackConfigDto'
        subtitles:
          type: boolean
          description: Enable subtitles generation for this transcription
          default: false
        subtitles_config:
          description: Configuration for subtitles generation if `subtitles` is enabled
          allOf:
          - $ref: '#/components/schemas/SubtitlesConfigDTO'
        diarization:
          type: boolean
          description: Enable speaker recognition (diarization) for this audio
          default: false
        diarization_config:
          description: Speaker recognition configuration, if `diarization` is enabled
          allOf:
          - $ref: '#/components/schemas/DiarizationConfigDTO'
        translation:
          type: boolean
          description: '**[Beta]** Enable translation for this audio'
          default: false
        translation_config:
          description: '**[Beta]** Translation configuration, if `translation` is enabled'
          allOf:
          - $ref: '#/components/schemas/TranslationConfigDTO'
        summarization:
          type: boolean
          description: Enable summarization for this audio
          default: false
        summarization_config:
          description: Summarization configuration, if `summarization` is enabled
          allOf:
          - $ref: '#/components/schemas/SummarizationConfigDTO'
        named_entity_recognition:
          type: boolean
          description: '**[Alpha]** Enable named entity recognition for this audio'
          default: false
        custom_spelling:
          type: boolean
          description: '**[Alpha]** Enable custom spelling for this audio'
          default: false
        custom_spelling_config:
          description: '**[Alpha]** Custom spelling configuration, if `custom_spelling` is enabled'
          allOf:
          - $ref: '#/components/schemas/CustomSpellingConfigDTO'
        sentiment_analysis:
          type: boolean
          description: Enable sentiment analysis for this audio
          default: false
        audio_to_llm:
          type: boolean
          description: Enable audio to LLM processing for this audio
          default: false
        audio_to_llm_config:
          description: Audio to LLM configuration, if `audio_to_llm` is enabled
          allOf:
          - $ref: '#/components/schemas/AudioToLlmListConfigDTO'
        pii_redaction:
          type: boolean
          description: Enable PII redaction for this audio
          default: false
        pii_redaction_config:
          description: PII redaction configuration, if `pii_redaction` is enabled
          allOf:
          - $ref: '#/components/schemas/PiiRedactionConfigDTO'
        sentences:
          type: boolean
          description: Enable sentences for this audio
          default: false
        punctuation_enhanced:
          type: boolean
          description: '**[Alpha]** Use enhanced punctuation for this audio'
          default: false
        language_config:
          description: Specify the language configuration
          allOf:
          - $ref: '#/components/schemas/LanguageConfig'
        audio_url:
          type: string
          format: uri
          nullable: true
      required:
      - audio_url
    TranscriptionMetadataDTO:
      type: object
      properties:
        audio_duration:
          type: number
          description: Duration of the transcribed audio file
          example: 3600
        number_of_distinct_channels:
          type: integer
          description: Number of distinct channels in the transcribed audio file
          minimum: 1
          example: 1
        billing_time:
          type: number
          description: Billed duration in seconds (audio_duration * number_of_distinct_channels)
          example: 3600
        transcription_time:
          type: number
          description: Duration of the transcription in seconds
          example: 20
      required:
      - audio_duration
      - number_of_distinct_channels
      - billing_time
      - transcription_time
    AddonErrorDTO:
      type: object
      properties:
        status_code:
          type: integer
          description: Status code of the addon error
          example: 500
        exception:
          type: string
          description: Reason of the addon error
        message:
          type: string
          description: Detailed message of the addon error
      required:
      - status_code
      - exception
      - message
    SentencesDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: If `sentences` has been enabled, transcription as sentences.
          nullable: true
          type: array
          items:
            type: string
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    SubtitleDTO:
      type: object
      properties:
        format:
          description: Format of the current subtitle
          example: srt
          allOf:
          - $ref: '#/components/schemas/SubtitlesFormatEnum'
        subtitles:
          type: string
          description: Transcription on the asked subtitle format
      required:
      - format
      - subtitles
    WordDTO:
      type: object
      properties:
        word:
          type: string
          description: Spoken word
        start:
          type: number
          description: Start timestamps in seconds of the spoken word
        end:
          type: number
          description: End timestamps in seconds of the spoken word
        confidence:
          type: number
          description: Confidence on the transcribed word (1 = 100% confident)
      required:
      - word
      - start
      - end
      - confidence
    UtteranceDTO:
      type: object
      properties:
        start:
          type: number
          description: Start timestamp in seconds of this utterance
        end:
          type: number
          description: End timestamp in seconds of this utterance
        confidence:
          type: number
          description: Confidence on the transcribed utterance (1 = 100% confident)
        channel:
          type: integer
          description: Audio channel of where this utterance has been transcribed from
          minimum: 0
        speaker:
          type: integer
          description: If `diarization` enabled, speaker identification number
          minimum: 0
        words:
          description: List of words of the utterance, split by timestamp
          type: array
          items:
            $ref: '#/components/schemas/WordDTO'
        text:
          type: string
          description: Transcription for this utterance
        language:
          description: Spoken language in this utterance
          example: en
          allOf:
          - $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
      required:
      - start
      - end
      - confidence
      - channel
      - words
      - text
      - language
    TranscriptionDTO:
      type: object
      properties:
        full_transcript:
          type: string
          description: All transcription on text format without any other information
        languages:
          type: array
          description: All the detected languages in the audio sorted from the most detected to the less detected
          example:
          - en
          items:
            $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
        sentences:
          description: If `sentences` has been enabled, sentences results
          type: array
          items:
            $ref: '#/components/schemas/SentencesDTO'
        subtitles:
          description: If `subtitles` has been enabled, subtitles results
          type: array
          items:
            $ref: '#/components/schemas/SubtitleDTO'
        utterances:
          description: Transcribed speech utterances present in the audio
          type: array
          items:
            $ref: '#/components/schemas/UtteranceDTO'
      required:
      - full_transcript
      - languages
      - utterances
    TranslationResultDTO:
      type: object
      properties:
        error:
          description: Contains the error details of the failed addon
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        full_transcript:
          type: string
          description: All transcription on text format without any other information
        languages:
          type: array
          description: All the detected languages in the audio sorted from the most detected to the less detected
          example:
          - en
          items:
            $ref: '#/components/schemas/TranslationLanguageCodeEnum'
        sentences:
          description: If `sentences` has been enabled, sentences results for this translation
          type: array
          items:
            $ref: '#/components/schemas/SentencesDTO'
        subtitles:
          description: If `subtitles` has been enabled, subtitles results for this translation
          type: array
          items:
            $ref: '#/components/schemas/SubtitleDTO'
        utterances:
          description: Transcribed speech utterances present in the audio
          type: array
          items:
            $ref: '#/components/schemas/UtteranceDTO'
      required:
      - error
      - full_transcript
      - languages
      - utterances
    TranslationDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: List of translated transcriptions, one for each `target_languages`
          nullable: true
          type: array
          items:
            $ref: '#/components/schemas/TranslationResultDTO'
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    SummarizationDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          type: string
          description: If `summarization` has been enabled, summary of the transcription
          nullable: true
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    ModerationDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          type: string
          description: If `moderation` has been enabled, moderated transcription
          nullable: true
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    NamedEntityRecognitionResult:
      type: object
      properties:
        entity_type:
          type: string
        text:
          type: string
        start:
          type: number
        end:
          type: number
      required:
      - entity_type
      - text
      - start
      - end
    NamedEntityRecognitionDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: If `named_entity_recognition` has been enabled, the detected entities.
          nullable: true
          type: array
          items:
            $ref: '#/components/schemas/NamedEntityRecognitionResult'
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    NamesConsistencyDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          type: string
          description: Deprecated, If `name_consistency` has been enabled, Gladia will improve the consistency of the names
            across the transcription
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    StructuredDataExtractionDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          type: string
          description: If `structured_data_extraction` has been enabled, results of the AI structured data extraction for
            the defined classes.
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    SentimentAnalysisDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          type: string
          description: If `sentiment_analysis` has been enabled, Gladia will analyze the sentiments and emotions of the audio
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    AudioToLlmResultDTO:
      type: object
      properties:
        prompt:
          type: string
          description: The prompt used
          nullable: true
        response:
          type: string
          description: The result of the AI analysis
          nullable: true
      required:
      - prompt
      - response
    AudioToLlmDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: The result from a specific prompt
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AudioToLlmResultDTO'
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    AudioToLlmListDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: If `audio_to_llm` has been enabled, results of the AI custom analysis
          nullable: true
          type: array
          items:
            $ref: '#/components/schemas/AudioToLlmDTO'
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    DisplayModeDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: If `display_mode` has been enabled, proposes an alternative display output.
          nullable: true
          type: array
          items:
            type: string
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    ChapterizationDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          type: object
          description: If `chapterization` has been enabled, will generate chapters name for different parts of the given
            audio.
          additionalProperties: true
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    DiarizationDTO:
      type: object
      properties:
        success:
          type: boolean
          description: The audio intelligence model succeeded to get a valid output
        is_empty:
          type: boolean
          description: The audio intelligence model returned an empty value
        exec_time:
          type: number
          description: Time audio intelligence model took to complete the task
        error:
          description: '`null` if `success` is `true`. Contains the error details of the failed model'
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AddonErrorDTO'
        results:
          description: '[Deprecated] If `diarization` has been enabled, the diarization result will appear here'
          type: array
          items:
            $ref: '#/components/schemas/UtteranceDTO'
      required:
      - success
      - is_empty
      - exec_time
      - error
      - results
    TranscriptionResultDTO:
      type: object
      properties:
        metadata:
          description: Metadata for the given transcription & audio file
          allOf:
          - $ref: '#/components/schemas/TranscriptionMetadataDTO'
        transcription:
          description: Transcription of the audio speech
          allOf:
          - $ref: '#/components/schemas/TranscriptionDTO'
        translation:
          description: If `translation` has been enabled, translation of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/TranslationDTO'
        summarization:
          description: If `summarization` has been enabled, summarization of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/SummarizationDTO'
        moderation:
          description: If `moderation` has been enabled, moderation of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/ModerationDTO'
        named_entity_recognition:
          description: If `named_entity_recognition` has been enabled, the detected entities
          allOf:
          - $ref: '#/components/schemas/NamedEntityRecognitionDTO'
        name_consistency:
          description: If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription
          allOf:
          - $ref: '#/components/schemas/NamesConsistencyDTO'
        structured_data_extraction:
          description: If `structured_data_extraction` has been enabled, structured data extraction results
          allOf:
          - $ref: '#/components/schemas/StructuredDataExtractionDTO'
        sentiment_analysis:
          description: If `sentiment_analysis` has been enabled, sentiment analysis of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/SentimentAnalysisDTO'
        audio_to_llm:
          description: If `audio_to_llm` has been enabled, audio to llm results of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/AudioToLlmListDTO'
        sentences:
          description: 'If `sentences` has been enabled, sentences of the audio speech transcription. Deprecated: content
            will move to the `transcription` object.'
          deprecated: true
          allOf:
          - $ref: '#/components/schemas/SentencesDTO'
        display_mode:
          description: If `display_mode` has been enabled, the output will be reordered, creating new utterances when speakers
            overlapped
          allOf:
          - $ref: '#/components/schemas/DisplayModeDTO'
        chapterization:
          description: If `chapterization` has been enabled, will generate chapters name for different parts of the given
            audio.
          allOf:
          - $ref: '#/components/schemas/ChapterizationDTO'
        diarization:
          description: If `diarization` has been requested and an error has occurred, the result will appear here
          allOf:
          - $ref: '#/components/schemas/DiarizationDTO'
      required:
      - metadata
    PreRecordedResponse:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-45463597
        version:
          type: integer
          description: API version
          example: 2
        status:
          type: string
          description: '"queued": the job has been queued. "processing": the job is being processed. "done": the job has been
            processed and the result is available. "error": an error occurred during the job''s processing.'
          enum:
          - queued
          - processing
          - done
          - error
        created_at:
          type: string
          description: Creation date
          format: date-time
          example: '2023-12-28T09:04:17.210Z'
        completed_at:
          type: string
          description: Completion date when status is "done" or "error"
          format: date-time
          example: '2023-12-28T09:04:37.210Z'
          nullable: true
        custom_metadata:
          type: object
          description: Custom metadata given in the initial request
          example:
            user: John Doe
          additionalProperties: true
        error_code:
          type: integer
          description: HTTP status code of the error if status is "error"
          minimum: 400
          maximum: 599
          example: 500
          nullable: true
        post_session_metadata:
          type: object
          description: For debugging purposes, send data that could help to identify issues
        kind:
          type: string
          enum:
          - pre-recorded
          example: pre-recorded
          default: pre-recorded
        file:
          description: The file data you uploaded. Can be null if status is "error"
          nullable: true
          allOf:
          - $ref: '#/components/schemas/FileResponse'
        request_params:
          description: Parameters used for this pre-recorded transcription. Can be null if status is "error"
          nullable: true
          allOf:
          - $ref: '#/components/schemas/PreRecordedRequestParamsResponse'
        result:
          description: Pre-recorded transcription's result when status is "done"
          nullable: true
          allOf:
          - $ref: '#/components/schemas/TranscriptionResultDTO'
      required:
      - id
      - request_id
      - version
      - status
      - created_at
      - post_session_metadata
      - kind
    NotFoundErrorResponse:
      type: object
      properties:
        timestamp:
          type: string
          description: Date of when the error occurred
          example: '2023-12-28T09:04:17.210Z'
        path:
          type: string
          description: Path to the API endpoint
          example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-821fe9df
        statusCode:
          type: number
          description: HTTP status code of the error
          example: 404
        message:
          type: string
          description: Error message
          example: Not found
      required:
      - timestamp
      - path
      - request_id
      - statusCode
      - message
    ListPreRecordedResponse:
      type: object
      properties:
        first:
          type: string
          description: URL to fetch the first page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        current:
          type: string
          description: URL to fetch the current page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        next:
          type: string
          description: URL to fetch the next page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=20&limit=20
          nullable: true
        items:
          description: List of pre-recorded transcriptions
          type: array
          items:
            $ref: '#/components/schemas/PreRecordedResponse'
      required:
      - first
      - current
      - next
      - items
    ForbiddenErrorResponse:
      type: object
      properties:
        timestamp:
          type: string
          description: Date of when the error occurred
          example: '2023-12-28T09:04:17.210Z'
        path:
          type: string
          description: Path to the API endpoint
          example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-821fe9df
        statusCode:
          type: number
          description: HTTP status code of the error
          example: 403
        message:
          type: string
          description: Forbidden request
          example: Invalid parameter
      required:
      - timestamp
      - path
      - request_id
      - statusCode
      - message
    CallbackTranscriptionSuccessPayload:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          description: Type of event
          enum:
          - transcription.success
          example: transcription.success
          default: transcription.success
        payload:
          description: Result of the transcription
          allOf:
          - $ref: '#/components/schemas/TranscriptionResultDTO'
        custom_metadata:
          type: object
          description: Custom metadata given in the initial request
          nullable: true
          example:
            user: John Doe
          additionalProperties: true
      required:
      - id
      - event
      - payload
    ErrorDTO:
      type: object
      properties:
        code:
          type: integer
          description: Error code
          example: 400
        message:
          type: string
          description: Error message
          example: Bad Request
      required:
      - code
      - message
    CallbackTranscriptionErrorPayload:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          description: Type of event
          enum:
          - transcription.error
          example: transcription.error
          default: transcription.error
        error:
          description: The error that occurred during the transcription
          allOf:
          - $ref: '#/components/schemas/ErrorDTO'
        custom_metadata:
          type: object
          description: Custom metadata given in the initial request
          nullable: true
          example:
            user: John Doe
          additionalProperties: true
      required:
      - id
      - event
      - error
    StreamingSupportedEncodingEnum:
      type: string
      enum:
      - wav/pcm
      - wav/alaw
      - wav/ulaw
      description: "The encoding format of the audio stream. Supported formats: \n- PCM: 8, 16, 24, and 32 bits \n- A-law:\
        \ 8 bits \n- μ-law: 8 bits \n\nNote: No need to add WAV headers to raw audio as the API supports both formats."
    StreamingSupportedBitDepthEnum:
      type: number
      enum:
      - 8
      - 16
      - 24
      - 32
      description: The bit depth of the audio stream
    StreamingSupportedSampleRateEnum:
      type: number
      enum:
      - 8000
      - 16000
      - 32000
      - 44100
      - 48000
      description: The sample rate of the audio stream
    StreamingSupportedModels:
      type: string
      enum:
      - solaria-1
      description: The model used to process the audio. "solaria-1" is used by default.
    PreProcessingConfig:
      type: object
      properties:
        audio_enhancer:
          type: boolean
          description: If true, apply pre-processing to the audio stream to enhance the quality.
          default: false
        speech_threshold:
          type: number
          description: Sensitivity configuration for Speech Threshold. A value close to 1 will apply stricter thresholds,
            making it less likely to detect background sounds as speech.
          default: 0.6
          minimum: 0
          maximum: 1
    RealtimeProcessingConfig:
      type: object
      properties:
        custom_vocabulary:
          type: boolean
          description: If true, enable custom vocabulary for the transcription.
          default: false
        custom_vocabulary_config:
          description: Custom vocabulary configuration, if `custom_vocabulary` is enabled
          allOf:
          - $ref: '#/components/schemas/CustomVocabularyConfigDTO'
        custom_spelling:
          type: boolean
          description: If true, enable custom spelling for the transcription.
          default: false
        custom_spelling_config:
          description: Custom spelling configuration, if `custom_spelling` is enabled
          allOf:
          - $ref: '#/components/schemas/CustomSpellingConfigDTO'
        translation:
          type: boolean
          description: If true, enable translation for the transcription
          default: false
        translation_config:
          description: Translation configuration, if `translation` is enabled
          allOf:
          - $ref: '#/components/schemas/TranslationConfigDTO'
        named_entity_recognition:
          type: boolean
          description: If true, enable named entity recognition for the transcription.
          default: false
        sentiment_analysis:
          type: boolean
          description: If true, enable sentiment analysis for the transcription.
          default: false
    PostProcessingConfig:
      type: object
      properties:
        summarization:
          type: boolean
          description: If true, generates summarization for the whole transcription.
          default: false
        summarization_config:
          description: Summarization configuration, if `summarization` is enabled
          allOf:
          - $ref: '#/components/schemas/SummarizationConfigDTO'
        chapterization:
          type: boolean
          description: If true, generates chapters for the whole transcription.
          default: false
    MessagesConfig:
      type: object
      properties:
        receive_partial_transcripts:
          type: boolean
          description: If true, partial transcript will be sent to websocket.
          default: false
        receive_final_transcripts:
          type: boolean
          description: If true, final transcript will be sent to websocket.
          default: true
        receive_speech_events:
          type: boolean
          description: If true, begin and end speech events will be sent to websocket.
          default: true
        receive_pre_processing_events:
          type: boolean
          description: If true, pre-processing events will be sent to websocket.
          default: true
        receive_realtime_processing_events:
          type: boolean
          description: If true, realtime processing events will be sent to websocket.
          default: true
        receive_post_processing_events:
          type: boolean
          description: If true, post-processing events will be sent to websocket.
          default: true
        receive_acknowledgments:
          type: boolean
          description: If true, acknowledgments will be sent to websocket.
          default: true
        receive_errors:
          type: boolean
          description: If true, errors will be sent to websocket.
          default: true
        receive_lifecycle_events:
          type: boolean
          description: If true, lifecycle events will be sent to websocket.
          default: false
    CallbackConfig:
      type: object
      properties:
        url:
          type: string
          description: URL on which we will do a `POST` request with configured messages
          example: https://callback.example
          format: uri
        receive_partial_transcripts:
          type: boolean
          description: If true, partial transcript will be sent to the defined callback.
          default: false
        receive_final_transcripts:
          type: boolean
          description: If true, final transcript will be sent to the defined callback.
          default: true
        receive_speech_events:
          type: boolean
          description: If true, begin and end speech events will be sent to the defined callback.
          default: false
        receive_pre_processing_events:
          type: boolean
          description: If true, pre-processing events will be sent to the defined callback.
          default: true
        receive_realtime_processing_events:
          type: boolean
          description: If true, realtime processing events will be sent to the defined callback.
          default: true
        receive_post_processing_events:
          type: boolean
          description: If true, post-processing events will be sent to the defined callback.
          default: true
        receive_acknowledgments:
          type: boolean
          description: If true, acknowledgments will be sent to the defined callback.
          default: false
        receive_errors:
          type: boolean
          description: If true, errors will be sent to the defined callback.
          default: false
        receive_lifecycle_events:
          type: boolean
          description: If true, lifecycle events will be sent to the defined callback.
          default: true
    StreamingRequestParamsResponse:
      type: object
      properties:
        encoding:
          description: "The encoding format of the audio stream. Supported formats: \n- PCM: 8, 16, 24, and 32 bits \n- A-law:\
            \ 8 bits \n- μ-law: 8 bits \n\nNote: No need to add WAV headers to raw audio as the API supports both formats."
          default: wav/pcm
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedEncodingEnum'
        bit_depth:
          description: The bit depth of the audio stream
          default: 16
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedBitDepthEnum'
        sample_rate:
          description: The sample rate of the audio stream
          default: 16000
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedSampleRateEnum'
        channels:
          type: integer
          description: The number of channels of the audio stream
          default: 1
          minimum: 1
          maximum: 8
        model:
          description: The model used to process the audio. "solaria-1" is used by default.
          default: solaria-1
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedModels'
        endpointing:
          type: number
          description: The endpointing duration in seconds. Endpointing is the duration of silence which will cause an utterance
            to be considered as finished
          default: 0.05
          minimum: 0.01
          maximum: 10
        maximum_duration_without_endpointing:
          type: number
          description: The maximum duration in seconds without endpointing. If endpointing is not detected after this duration,
            current utterance will be considered as finished
          default: 5
          minimum: 5
          maximum: 60
        language_config:
          description: Specify the language configuration
          allOf:
          - $ref: '#/components/schemas/LanguageConfig'
        pre_processing:
          description: Specify the pre-processing configuration
          allOf:
          - $ref: '#/components/schemas/PreProcessingConfig'
        realtime_processing:
          description: Specify the realtime processing configuration
          allOf:
          - $ref: '#/components/schemas/RealtimeProcessingConfig'
        post_processing:
          description: Specify the post-processing configuration
          allOf:
          - $ref: '#/components/schemas/PostProcessingConfig'
        messages_config:
          description: Specify the websocket messages configuration
          allOf:
          - $ref: '#/components/schemas/MessagesConfig'
        callback:
          type: boolean
          description: If true, messages will be sent to configured url.
          default: false
        callback_config:
          description: Specify the callback configuration
          allOf:
          - $ref: '#/components/schemas/CallbackConfig'
    StreamingTranscriptionResultWithMessagesDTO:
      type: object
      properties:
        metadata:
          description: Metadata for the given transcription & audio file
          allOf:
          - $ref: '#/components/schemas/TranscriptionMetadataDTO'
        transcription:
          description: Transcription of the audio speech
          allOf:
          - $ref: '#/components/schemas/TranscriptionDTO'
        translation:
          description: If `translation` has been enabled, translation of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/TranslationDTO'
        summarization:
          description: If `summarization` has been enabled, summarization of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/SummarizationDTO'
        named_entity_recognition:
          description: If `named_entity_recognition` has been enabled, the detected entities
          allOf:
          - $ref: '#/components/schemas/NamedEntityRecognitionDTO'
        sentiment_analysis:
          description: If `sentiment_analysis` has been enabled, sentiment analysis of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/SentimentAnalysisDTO'
        chapterization:
          description: If `chapterization` has been enabled, will generate chapters name for different parts of the given
            audio.
          allOf:
          - $ref: '#/components/schemas/ChapterizationDTO'
        messages:
          description: Real-Time messages sent by the server during the live transcription
          type: array
          items:
            type: string
      required:
      - metadata
    StreamingResponse:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-45463597
        version:
          type: integer
          description: API version
          example: 2
        status:
          type: string
          description: '"queued": the job has been queued. "processing": the job is being processed. "done": the job has been
            processed and the result is available. "error": an error occurred during the job''s processing.'
          enum:
          - queued
          - processing
          - done
          - error
        created_at:
          type: string
          description: Creation date
          format: date-time
          example: '2023-12-28T09:04:17.210Z'
        completed_at:
          type: string
          description: Completion date when status is "done" or "error"
          format: date-time
          example: '2023-12-28T09:04:37.210Z'
          nullable: true
        custom_metadata:
          type: object
          description: Custom metadata given in the initial request
          example:
            user: John Doe
          additionalProperties: true
        error_code:
          type: integer
          description: HTTP status code of the error if status is "error"
          minimum: 400
          maximum: 599
          example: 500
          nullable: true
        post_session_metadata:
          type: object
          description: For debugging purposes, send data that could help to identify issues
        kind:
          type: string
          enum:
          - live
          example: live
          default: live
        file:
          description: The file data you uploaded. Can be null if status is "error"
          nullable: true
          allOf:
          - $ref: '#/components/schemas/FileResponse'
        request_params:
          description: Parameters used for this live transcription. Can be null if status is "error"
          nullable: true
          allOf:
          - $ref: '#/components/schemas/StreamingRequestParamsResponse'
        result:
          description: Live transcription's result when status is "done"
          nullable: true
          allOf:
          - $ref: '#/components/schemas/StreamingTranscriptionResultWithMessagesDTO'
      required:
      - id
      - request_id
      - version
      - status
      - created_at
      - post_session_metadata
      - kind
    ListTranscriptionResponse:
      type: object
      properties:
        first:
          type: string
          description: URL to fetch the first page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        current:
          type: string
          description: URL to fetch the current page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        next:
          type: string
          description: URL to fetch the next page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=20&limit=20
          nullable: true
        items:
          description: List of transcriptions
          discriminator:
            propertyName: kind
            mapping:
              pre-recorded: '#/components/schemas/PreRecordedResponse'
              live: '#/components/schemas/StreamingResponse'
          type: array
          items:
            oneOf:
            - $ref: '#/components/schemas/PreRecordedResponse'
            - $ref: '#/components/schemas/StreamingResponse'
      required:
      - first
      - current
      - next
      - items
    ListHistoryResponse:
      type: object
      properties:
        first:
          type: string
          description: URL to fetch the first page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        current:
          type: string
          description: URL to fetch the current page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        next:
          type: string
          description: URL to fetch the next page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=20&limit=20
          nullable: true
        items:
          description: List of jobs
          discriminator:
            propertyName: kind
            mapping:
              pre-recorded: '#/components/schemas/PreRecordedResponse'
              live: '#/components/schemas/StreamingResponse'
          type: array
          items:
            oneOf:
            - $ref: '#/components/schemas/PreRecordedResponse'
            - $ref: '#/components/schemas/StreamingResponse'
      required:
      - first
      - current
      - next
      - items
    AudioChunkActionData:
      type: object
      properties:
        chunk:
          type: string
          description: Chunk encoded in base64. The chunk must contains complete frames
          example: aGVsbG8=
      required:
      - chunk
    AudioChunkAction:
      type: object
      properties:
        type:
          type: string
          enum:
          - audio_chunk
          example: audio_chunk
          default: audio_chunk
        data:
          description: Payload of the audio chunk action
          allOf:
          - $ref: '#/components/schemas/AudioChunkActionData'
      required:
      - type
      - data
    StopRecordingAction:
      type: object
      properties:
        type:
          type: string
          enum:
          - stop_recording
          example: stop_recording
          default: stop_recording
      required:
      - type
    Error:
      type: object
      properties:
        message:
          type: string
          description: The error message
      required:
      - message
    AudioChunkAckData:
      type: object
      properties:
        byte_range:
          description: Range in bytes length of the audio chunk (relative to the whole session)
          minItems: 2
          maxItems: 2
          example:
          - 1024
          - 2048
          type: array
          items:
            type: integer
        time_range:
          description: Range in seconds of the audio chunk (relative to the whole session)
          minItems: 2
          maxItems: 2
          example:
          - 0.8
          - 0.9
          type: array
          items:
            type: number
      required:
      - byte_range
      - time_range
    AudioChunkAckMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        acknowledged:
          type: boolean
          description: Flag to indicate if the action was successfully acknowledged
          example: true
        error:
          description: Error message if the action was not successfully acknowledged
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - audio_chunk
          example: audio_chunk
          default: audio_chunk
        data:
          description: The message data. "null" if the action was not successfully acknowledged
          nullable: true
          allOf:
          - $ref: '#/components/schemas/AudioChunkAckData'
      required:
      - session_id
      - created_at
      - acknowledged
      - error
      - type
      - data
    CallbackLiveAudioChunkAckMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.audio_chunk
          example: live.audio_chunk
          default: live.audio_chunk
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/AudioChunkAckMessage'
      required:
      - id
      - event
      - payload
    EndRecordingMessageData:
      type: object
      properties:
        recording_duration:
          type: number
          description: Total audio duration in seconds
          example: 344.45
      required:
      - recording_duration
    EndRecordingMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - end_recording
          example: end_recording
          default: end_recording
        data:
          description: The message data
          allOf:
          - $ref: '#/components/schemas/EndRecordingMessageData'
      required:
      - session_id
      - created_at
      - type
      - data
    CallbackLiveEndRecordingMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.end_recording
          example: live.end_recording
          default: live.end_recording
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/EndRecordingMessage'
      required:
      - id
      - event
      - payload
    EndSessionMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - end_session
          example: end_session
          default: end_session
      required:
      - session_id
      - created_at
      - type
    CallbackLiveEndSessionMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.end_session
          example: live.end_session
          default: live.end_session
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/EndSessionMessage'
      required:
      - id
      - event
      - payload
    TranslationData:
      type: object
      properties:
        utterance_id:
          type: string
          description: Id of the utterance used for this result
          example: 00-00000011
        utterance:
          description: The transcribed utterance
          allOf:
          - $ref: '#/components/schemas/UtteranceDTO'
        original_language:
          description: The original language in `iso639-1` or `iso639-2` format depending on the language
          allOf:
          - $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
        target_language:
          description: The target language in `iso639-1` or `iso639-2` format depending on the language
          allOf:
          - $ref: '#/components/schemas/TranslationLanguageCodeEnum'
        translated_utterance:
          description: The translated utterance
          allOf:
          - $ref: '#/components/schemas/UtteranceDTO'
      required:
      - utterance_id
      - utterance
      - original_language
      - target_language
      - translated_utterance
    TranslationMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        error:
          description: Error message if the addon failed
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - translation
          example: translation
          default: translation
        data:
          description: The message data. "null" if the addon failed
          nullable: true
          allOf:
          - $ref: '#/components/schemas/TranslationData'
      required:
      - session_id
      - created_at
      - error
      - type
      - data
    CallbackLiveTranslationMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.translation
          example: live.translation
          default: live.translation
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/TranslationMessage'
      required:
      - id
      - event
      - payload
    NamedEntityRecognitionData:
      type: object
      properties:
        utterance_id:
          type: string
          description: Id of the utterance used for this result
          example: 00-00000011
        utterance:
          description: The transcribed utterance
          allOf:
          - $ref: '#/components/schemas/UtteranceDTO'
        results:
          description: The NER results
          type: array
          items:
            $ref: '#/components/schemas/NamedEntityRecognitionResult'
      required:
      - utterance_id
      - utterance
      - results
    NamedEntityRecognitionMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        error:
          description: Error message if the addon failed
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - named_entity_recognition
          example: named_entity_recognition
          default: named_entity_recognition
        data:
          description: The message data. "null" if the addon failed
          nullable: true
          allOf:
          - $ref: '#/components/schemas/NamedEntityRecognitionData'
      required:
      - session_id
      - created_at
      - error
      - type
      - data
    CallbackLiveNamedEntityRecognitionMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.named_entity_recognition
          example: live.named_entity_recognition
          default: live.named_entity_recognition
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/NamedEntityRecognitionMessage'
      required:
      - id
      - event
      - payload
    ChapterizationSentence:
      type: object
      properties:
        sentence:
          type: string
        start:
          type: number
        end:
          type: number
        words:
          type: array
          items:
            $ref: '#/components/schemas/WordDTO'
      required:
      - sentence
      - start
      - end
      - words
    PostChapterizationResult:
      type: object
      properties:
        abstractive_summary:
          type: string
        extractive_summary:
          type: string
        summary:
          type: string
        headline:
          type: string
        gist:
          type: string
        keywords:
          type: array
          items:
            type: string
        start:
          type: number
        end:
          type: number
        sentences:
          type: array
          items:
            $ref: '#/components/schemas/ChapterizationSentence'
        text:
          type: string
      required:
      - headline
      - gist
      - keywords
      - start
      - end
      - sentences
      - text
    PostChapterizationMessageData:
      type: object
      properties:
        results:
          description: The chapters
          type: array
          items:
            $ref: '#/components/schemas/PostChapterizationResult'
      required:
      - results
    PostChapterizationMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        error:
          description: Error message if the addon failed
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - post_chapterization
          example: post_chapterization
          default: post_chapterization
        data:
          description: The message data. "null" if the addon failed
          nullable: true
          allOf:
          - $ref: '#/components/schemas/PostChapterizationMessageData'
      required:
      - session_id
      - created_at
      - error
      - type
      - data
    CallbackLivePostChapterizationMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.post_chapterization
          example: live.post_chapterization
          default: live.post_chapterization
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/PostChapterizationMessage'
      required:
      - id
      - event
      - payload
    StreamingTranscriptionResultDTO:
      type: object
      properties:
        metadata:
          description: Metadata for the given transcription & audio file
          allOf:
          - $ref: '#/components/schemas/TranscriptionMetadataDTO'
        transcription:
          description: Transcription of the audio speech
          allOf:
          - $ref: '#/components/schemas/TranscriptionDTO'
        translation:
          description: If `translation` has been enabled, translation of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/TranslationDTO'
        summarization:
          description: If `summarization` has been enabled, summarization of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/SummarizationDTO'
        named_entity_recognition:
          description: If `named_entity_recognition` has been enabled, the detected entities
          allOf:
          - $ref: '#/components/schemas/NamedEntityRecognitionDTO'
        sentiment_analysis:
          description: If `sentiment_analysis` has been enabled, sentiment analysis of the audio speech transcription
          allOf:
          - $ref: '#/components/schemas/SentimentAnalysisDTO'
        chapterization:
          description: If `chapterization` has been enabled, will generate chapters name for different parts of the given
            audio.
          allOf:
          - $ref: '#/components/schemas/ChapterizationDTO'
      required:
      - metadata
    PostFinalTranscriptMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - post_final_transcript
          example: post_final_transcript
          default: post_final_transcript
        data:
          description: The message data
          allOf:
          - $ref: '#/components/schemas/StreamingTranscriptionResultDTO'
      required:
      - session_id
      - created_at
      - type
      - data
    CallbackLivePostFinalTranscriptMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.post_final_transcript
          example: live.post_final_transcript
          default: live.post_final_transcript
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/PostFinalTranscriptMessage'
      required:
      - id
      - event
      - payload
    PostSummarizationMessageData:
      type: object
      properties:
        results:
          type: string
          description: The summarization
      required:
      - results
    PostSummarizationMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        error:
          description: Error message if the addon failed
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - post_summarization
          example: post_summarization
          default: post_summarization
        data:
          description: The message data. "null" if the addon failed
          nullable: true
          allOf:
          - $ref: '#/components/schemas/PostSummarizationMessageData'
      required:
      - session_id
      - created_at
      - error
      - type
      - data
    CallbackLivePostSummarizationMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.post_summarization
          example: live.post_summarization
          default: live.post_summarization
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/PostSummarizationMessage'
      required:
      - id
      - event
      - payload
    PostTranscriptMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - post_transcript
          example: post_transcript
          default: post_transcript
        data:
          description: The message data
          allOf:
          - $ref: '#/components/schemas/TranscriptionDTO'
      required:
      - session_id
      - created_at
      - type
      - data
    CallbackLivePostTranscriptMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.post_transcript
          example: live.post_transcript
          default: live.post_transcript
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/PostTranscriptMessage'
      required:
      - id
      - event
      - payload
    SentimentAnalysisResult:
      type: object
      properties:
        sentiment:
          type: string
        emotion:
          type: string
        text:
          type: string
        start:
          type: number
        end:
          type: number
        channel:
          type: number
      required:
      - sentiment
      - emotion
      - text
      - start
      - end
      - channel
    SentimentAnalysisData:
      type: object
      properties:
        utterance_id:
          type: string
          description: Id of the utterance used for this result
          example: 00-00000011
        utterance:
          description: The transcribed utterance
          allOf:
          - $ref: '#/components/schemas/UtteranceDTO'
        results:
          description: The sentiment analysis results
          type: array
          items:
            $ref: '#/components/schemas/SentimentAnalysisResult'
      required:
      - utterance_id
      - utterance
      - results
    SentimentAnalysisMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        error:
          description: Error message if the addon failed
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - sentiment_analysis
          example: sentiment_analysis
          default: sentiment_analysis
        data:
          description: The message data. "null" if the addon failed
          nullable: true
          allOf:
          - $ref: '#/components/schemas/SentimentAnalysisData'
      required:
      - session_id
      - created_at
      - error
      - type
      - data
    CallbackLiveSentimentAnalysisMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.sentiment_analysis
          example: live.sentiment_analysis
          default: live.sentiment_analysis
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/SentimentAnalysisMessage'
      required:
      - id
      - event
      - payload
    StartRecordingMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - start_recording
          example: start_recording
          default: start_recording
      required:
      - session_id
      - created_at
      - type
    CallbackLiveStartRecordingMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.start_recording
          example: live.start_recording
          default: live.start_recording
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/StartRecordingMessage'
      required:
      - id
      - event
      - payload
    StartSessionMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - start_session
          example: start_session
          default: start_session
      required:
      - session_id
      - created_at
      - type
    CallbackLiveStartSessionMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.start_session
          example: live.start_session
          default: live.start_session
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/StartSessionMessage'
      required:
      - id
      - event
      - payload
    StopRecordingAckData:
      type: object
      properties:
        recording_duration:
          type: number
          description: Total audio duration in seconds
          example: 344.45
        recording_left_to_process:
          type: number
          description: Audio duration left to process in seconds
          example: 11.23
      required:
      - recording_duration
      - recording_left_to_process
    StopRecordingAckMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        acknowledged:
          type: boolean
          description: Flag to indicate if the action was successfully acknowledged
          example: true
        error:
          description: Error message if the action was not successfully acknowledged
          nullable: true
          example: null
          allOf:
          - $ref: '#/components/schemas/Error'
        type:
          type: string
          enum:
          - stop_recording
          example: stop_recording
          default: stop_recording
        data:
          description: The message data. "null" if the action was not successfully acknowledged
          nullable: true
          allOf:
          - $ref: '#/components/schemas/StopRecordingAckData'
      required:
      - session_id
      - created_at
      - acknowledged
      - error
      - type
      - data
    CallbackLiveStopRecordingAckMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.stop_recording
          example: live.stop_recording
          default: live.stop_recording
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/StopRecordingAckMessage'
      required:
      - id
      - event
      - payload
    TranscriptMessageData:
      type: object
      properties:
        id:
          type: string
          description: Id of the utterance
          example: 00-00000011
        is_final:
          type: boolean
          description: Flag to indicate if the transcript is final or not
          example: true
        utterance:
          description: The transcribed utterance
          allOf:
          - $ref: '#/components/schemas/UtteranceDTO'
      required:
      - id
      - is_final
      - utterance
    TranscriptMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - transcript
          example: transcript
          default: transcript
        data:
          description: The message data
          allOf:
          - $ref: '#/components/schemas/TranscriptMessageData'
      required:
      - session_id
      - created_at
      - type
      - data
    CallbackLiveTranscriptMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.transcript
          example: live.transcript
          default: live.transcript
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/TranscriptMessage'
      required:
      - id
      - event
      - payload
    SpeechMessageData:
      type: object
      properties:
        time:
          type: number
          description: Timestamp in seconds of the speech event
          example: 12.56
        channel:
          type: number
          description: Channel of the speech event
          example: 1
      required:
      - time
      - channel
    SpeechStartMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - speech_start
          example: speech_start
          default: speech_start
        data:
          description: The message data
          allOf:
          - $ref: '#/components/schemas/SpeechMessageData'
      required:
      - session_id
      - created_at
      - type
      - data
    CallbackLiveSpeechStartMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.speech_start
          example: live.speech_start
          default: live.speech_start
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/SpeechStartMessage'
      required:
      - id
      - event
      - payload
    SpeechEndMessage:
      type: object
      properties:
        session_id:
          type: string
          description: Id of the live session
          example: 4a39145c-2844-4557-8f34-34883f7be7d9
        created_at:
          type: string
          description: Date of creation of the message. The date is formatted as an ISO 8601 string
          example: '2021-09-01T12:00:00.123Z'
        type:
          type: string
          enum:
          - speech_end
          example: speech_end
          default: speech_end
        data:
          description: The message data
          allOf:
          - $ref: '#/components/schemas/SpeechMessageData'
      required:
      - session_id
      - created_at
      - type
      - data
    CallbackLiveSpeechEndMessage:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        event:
          type: string
          enum:
          - live.speech_end
          example: live.speech_end
          default: live.speech_end
        payload:
          description: The live message payload as sent to the WebSocket
          allOf:
          - $ref: '#/components/schemas/SpeechEndMessage'
      required:
      - id
      - event
      - payload
    StreamingRequest:
      type: object
      properties:
        encoding:
          description: "The encoding format of the audio stream. Supported formats: \n- PCM: 8, 16, 24, and 32 bits \n- A-law:\
            \ 8 bits \n- μ-law: 8 bits \n\nNote: No need to add WAV headers to raw audio as the API supports both formats."
          default: wav/pcm
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedEncodingEnum'
        bit_depth:
          description: The bit depth of the audio stream
          default: 16
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedBitDepthEnum'
        sample_rate:
          description: The sample rate of the audio stream
          default: 16000
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedSampleRateEnum'
        channels:
          type: integer
          description: The number of channels of the audio stream
          default: 1
          minimum: 1
          maximum: 8
        custom_metadata:
          type: object
          description: Custom metadata you can attach to this live transcription
          example:
            user: John Doe
          additionalProperties: true
        model:
          description: The model used to process the audio. "solaria-1" is used by default.
          default: solaria-1
          allOf:
          - $ref: '#/components/schemas/StreamingSupportedModels'
        endpointing:
          type: number
          description: The endpointing duration in seconds. Endpointing is the duration of silence which will cause an utterance
            to be considered as finished
          default: 0.05
          minimum: 0.01
          maximum: 10
        maximum_duration_without_endpointing:
          type: number
          description: The maximum duration in seconds without endpointing. If endpointing is not detected after this duration,
            current utterance will be considered as finished
          default: 5
          minimum: 5
          maximum: 60
        language_config:
          description: Specify the language configuration
          allOf:
          - $ref: '#/components/schemas/LanguageConfig'
        pre_processing:
          description: Specify the pre-processing configuration
          allOf:
          - $ref: '#/components/schemas/PreProcessingConfig'
        realtime_processing:
          description: Specify the realtime processing configuration
          allOf:
          - $ref: '#/components/schemas/RealtimeProcessingConfig'
        post_processing:
          description: Specify the post-processing configuration
          allOf:
          - $ref: '#/components/schemas/PostProcessingConfig'
        messages_config:
          description: Specify the websocket messages configuration
          allOf:
          - $ref: '#/components/schemas/MessagesConfig'
        callback:
          type: boolean
          description: If true, messages will be sent to configured url.
          default: false
        callback_config:
          description: Specify the callback configuration
          allOf:
          - $ref: '#/components/schemas/CallbackConfig'
    StreamingSupportedRegions:
      type: string
      enum:
      - us-west
      - eu-west
    InitStreamingResponse:
      type: object
      properties:
        id:
          type: string
          description: Id of the job
          format: uuid
          example: 45463597-20b7-4af7-b3b3-f5fb778203ab
        created_at:
          type: string
          description: Creation date
          format: date-time
          example: '2023-12-28T09:04:17.210Z'
        url:
          type: string
          description: The websocket url to connect to for sending audio data. The url will contain the temporary token to
            authenticate the session.
          example: wss://api.gladia.io/v2/live?token=4a39145c-2844-4557-8f34-34883f7be7d9
          format: uri
      required:
      - id
      - created_at
      - url
    ListStreamingResponse:
      type: object
      properties:
        first:
          type: string
          description: URL to fetch the first page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        current:
          type: string
          description: URL to fetch the current page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
        next:
          type: string
          description: URL to fetch the next page
          format: uri
          example: https://api.gladia.io/v2/transcription?status=done&offset=20&limit=20
          nullable: true
        items:
          description: List of live transcriptions
          type: array
          items:
            $ref: '#/components/schemas/StreamingResponse'
      required:
      - first
      - current
      - next
      - items
    PatchRequestParamsDTO:
      type: object
      properties: {}
    PayloadTooLargeErrorResponse:
      type: object
      properties:
        timestamp:
          type: string
          description: Date of when the error occurred
          example: '2023-12-28T09:04:17.210Z'
        path:
          type: string
          description: Path to the API endpoint
          example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
        request_id:
          type: string
          description: Debug id
          example: G-821fe9df
        statusCode:
          type: number
          description: HTTP status code of the error
          example: 413
        message:
          type: string
          description: Payload too large
          example: payload too large
      required:
      - timestamp
      - path
      - request_id
      - statusCode
      - message
    WebhookTranscriptionCreatedPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - transcription.created
          default: transcription.created
          example: transcription.created
        payload:
          $ref: '#/components/schemas/PreRecordedEventPayload'
      required:
      - event
      - payload
    WebhookTranscriptionSuccessPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - transcription.success
          default: transcription.success
          example: transcription.success
        payload:
          $ref: '#/components/schemas/PreRecordedEventPayload'
      required:
      - event
      - payload
    WebhookTranscriptionErrorPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - transcription.error
          default: transcription.error
          example: transcription.error
        payload:
          $ref: '#/components/schemas/PreRecordedEventPayload'
      required:
      - event
      - payload
    WebhookLiveStartSessionPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - live.start_session
          default: live.start_session
          example: live.start_session
        payload:
          $ref: '#/components/schemas/LiveEventPayload'
      required:
      - event
      - payload
    WebhookLiveStartRecordingPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - live.start_recording
          default: live.start_recording
          example: live.start_recording
        payload:
          $ref: '#/components/schemas/LiveEventPayload'
      required:
      - event
      - payload
    WebhookLiveEndRecordingPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - live.end_recording
          default: live.end_recording
          example: live.end_recording
        payload:
          $ref: '#/components/schemas/LiveEventPayload'
      required:
      - event
      - payload
    WebhookLiveEndSessionPayload:
      type: object
      properties:
        event:
          type: string
          enum:
          - live.end_session
          default: live.end_session
          example: live.end_session
        payload:
          $ref: '#/components/schemas/LiveEventPayload'
      required:
      - event
      - payload