openapi: 3.2.0
info:
  title: ElevenLabs API Documentation Text To Voice API
  description: This is the documentation for the ElevenLabs API. You can use this API to use our service programmatically, this is done by using your API key. You can find your API key in the dashboard at https://elevenlabs.io/app/settings/api-keys.
  version: '1.0'
tags:
- name: text-to-voice
  description: Design and generate custom voices from a text prompt.
paths:
  /v1/text-to-voice/create-previews:
    post:
      tags:
      - text-to-voice
      summary: '[Deprecated] Generate A Voice Preview From Description'
      description: '**Deprecated.** Use `POST /v1/text-to-voice/design` instead. Generate a custom voice based on voice description. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create the voice use `POST /v1/text-to-voice` with the chosen `generated_voice_id`.'
      operationId: text_to_voice
      deprecated: true
      parameters:
      - name: output_format
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/AllowedOutputFormats'
          title: Output format of the generated audio.
          description: Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
          enum:
          - mp3_22050_32
          - mp3_24000_48
          - mp3_44100_32
          - mp3_44100_64
          - mp3_44100_96
          - mp3_44100_128
          - mp3_44100_192
          - pcm_8000
          - pcm_16000
          - pcm_22050
          - pcm_24000
          - pcm_32000
          - pcm_44100
          - pcm_48000
          - ulaw_8000
          - alaw_8000
          - opus_48000_32
          - opus_48000_64
          - opus_48000_96
          - opus_48000_128
          - opus_48000_192
          default: mp3_44100_192
        description: Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
          title: Xi-Api-Key
        description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoicePreviewsRequestModel'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicePreviewsResponseModel'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-fern-sdk-group-name: text_to_voice
      x-fern-sdk-method-name: create_previews
  /v1/text-to-voice:
    post:
      tags:
      - text-to-voice
      summary: Create A New Voice From Voice Preview
      description: Create a voice from previously generated voice preview. This endpoint should be called after you fetched a generated_voice_id using POST /v1/text-to-voice/design or POST /v1/text-to-voice/:voice_id/remix.
      operationId: create_voice
      parameters:
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
          title: Xi-Api-Key
        description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Body_Create_a_new_voice_from_voice_preview_v1_text_to_voice_post'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoiceResponseModel'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-fern-sdk-group-name: text_to_voice
      x-fern-sdk-method-name: create
  /v1/text-to-voice/design:
    post:
      tags:
      - text-to-voice
      summary: Design A Voice
      description: Design a voice via a prompt. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create a voice use the generated_voice_id of the preferred preview with the /v1/text-to-voice endpoint.
      operationId: text_to_voice_design
      parameters:
      - name: output_format
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/AllowedOutputFormats'
          title: Output format of the generated audio.
          description: Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
          enum:
          - mp3_22050_32
          - mp3_24000_48
          - mp3_44100_32
          - mp3_44100_64
          - mp3_44100_96
          - mp3_44100_128
          - mp3_44100_192
          - pcm_8000
          - pcm_16000
          - pcm_22050
          - pcm_24000
          - pcm_32000
          - pcm_44100
          - pcm_48000
          - ulaw_8000
          - alaw_8000
          - opus_48000_32
          - opus_48000_64
          - opus_48000_96
          - opus_48000_128
          - opus_48000_192
          default: mp3_44100_192
        description: Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
          title: Xi-Api-Key
        description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoiceDesignRequestModel'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicePreviewsResponseModel'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-fern-sdk-group-name: text_to_voice
      x-fern-sdk-method-name: design
  /v1/text-to-voice/{voice_id}/remix:
    post:
      tags:
      - text-to-voice
      summary: Remix A Voice
      description: Remix an existing voice via a prompt. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create a voice use the generated_voice_id of the preferred preview with the /v1/text-to-voice endpoint.
      operationId: text_to_voice_remix
      parameters:
      - name: voice_id
        in: path
        required: true
        schema:
          type: string
          description: Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
          examples:
          - 21m00Tcm4TlvDq8ikWAM
          title: Voice Id
        description: Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
      - name: output_format
        in: query
        required: false
        schema:
          $ref: '#/components/schemas/AllowedOutputFormats'
          title: Output format of the generated audio.
          description: Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
          enum:
          - mp3_22050_32
          - mp3_24000_48
          - mp3_44100_32
          - mp3_44100_64
          - mp3_44100_96
          - mp3_44100_128
          - mp3_44100_192
          - pcm_8000
          - pcm_16000
          - pcm_22050
          - pcm_24000
          - pcm_32000
          - pcm_44100
          - pcm_48000
          - ulaw_8000
          - alaw_8000
          - opus_48000_32
          - opus_48000_64
          - opus_48000_96
          - opus_48000_128
          - opus_48000_192
          default: mp3_44100_192
        description: Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
          title: Xi-Api-Key
        description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoiceRemixRequestModel'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicePreviewsResponseModel'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-fern-sdk-group-name: text_to_voice
      x-fern-sdk-method-name: remix
  /v1/text-to-voice/{generated_voice_id}/stream:
    get:
      tags:
      - text-to-voice
      summary: Text To Voice Preview Streaming
      description: Stream a voice preview that was created via the /v1/text-to-voice/design endpoint.
      operationId: text_to_voice_preview_stream
      parameters:
      - name: generated_voice_id
        in: path
        required: true
        schema:
          type: string
          description: The generated_voice_id to stream.
          examples:
          - 37HceQefKmEi3bGovXjL
          embed: true
          title: Generated Voice Id
        description: The generated_voice_id to stream.
      - name: xi-api-key
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
          title: Xi-Api-Key
        description: Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.
      responses:
        '200':
          description: Streaming audio data
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-fern-sdk-group-name:
      - text_to_voice
      - preview
      x-fern-sdk-method-name: stream
      x-fern-streaming: true
components:
  schemas:
    Body_Create_a_new_voice_from_voice_preview_v1_text_to_voice_post:
      properties:
        voice_name:
          type: string
          title: Voice Name
          description: Name to use for the created voice.
          examples:
          - Sassy squeaky mouse
        voice_description:
          type: string
          maxLength: 1000
          minLength: 20
          title: Voice Description
          description: Description to use for the created voice.
          examples:
          - A sassy squeaky mouse
        generated_voice_id:
          type: string
          title: Generated Voice Id
          description: The generated_voice_id to create; obtain it from POST /v1/text-to-voice/design, POST /v1/text-to-voice/:voice_id/remix, or the response headers when generating previews.
          examples:
          - 37HceQefKmEi3bGovXjL
        labels:
          anyOf:
          - additionalProperties:
              type: string
            type: object
          - type: 'null'
          title: Labels
          description: Optional, metadata to add to the created voice. Defaults to None.
          examples:
          - language: en
          name: Voice metadata
        played_not_selected_voice_ids:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Played Not Selected Voice Ids
          description: List of voice ids that the user has played but not selected. Used for RLHF.
      type: object
      required:
      - voice_name
      - voice_description
      - generated_voice_id
      title: Body_Create_a_new_voice_from_voice_preview_v1_text_to_voice_post
    VoicePreviewResponseModel:
      properties:
        audio_base_64:
          type: string
          title: Audio Base 64
          description: The base64 encoded audio of the preview.
        generated_voice_id:
          type: string
          title: Generated Voice Id
          description: The ID of the generated voice. Use it to create a voice from the preview.
        media_type:
          type: string
          title: Media Type
          description: The media type of the preview.
        duration_secs:
          type: number
          title: Duration Secs
          description: The duration of the preview in seconds.
        language:
          anyOf:
          - type: string
          - type: 'null'
          title: Language
          description: The language of the preview.
      type: object
      required:
      - audio_base_64
      - generated_voice_id
      - media_type
      - duration_secs
      - language
      title: VoicePreviewResponseModel
    SampleResponseModel:
      properties:
        sample_id:
          type: string
          title: Sample Id
          description: The ID of the sample.
        file_name:
          type: string
          title: File Name
          description: The name of the sample file.
        mime_type:
          type: string
          title: Mime Type
          description: The MIME type of the sample file.
        size_bytes:
          type: integer
          title: Size Bytes
          description: The size of the sample file in bytes.
        hash:
          type: string
          title: Hash
          description: The hash of the sample file.
        duration_secs:
          anyOf:
          - type: number
          - type: 'null'
          title: Duration Secs
        remove_background_noise:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Remove Background Noise
        has_isolated_audio:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Has Isolated Audio
        has_isolated_audio_preview:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Has Isolated Audio Preview
        speaker_separation:
          anyOf:
          - $ref: '#/components/schemas/SpeakerSeparationResponseModel'
          - type: 'null'
        trim_start:
          anyOf:
          - type: integer
          - type: 'null'
          title: Trim Start
        trim_end:
          anyOf:
          - type: integer
          - type: 'null'
          title: Trim End
      type: object
      required:
      - sample_id
      - file_name
      - mime_type
      - size_bytes
      - hash
      title: SampleResponseModel
      example:
        file_name: sample.mp3
        hash: '1234567890'
        mime_type: audio/mpeg
        sample_id: DCwhRBWXzGAHq8TQ4Fs18
        size_bytes: 1000000
    ManualVerificationResponseModel:
      properties:
        extra_text:
          type: string
          title: Extra Text
          description: The extra text of the manual verification.
        request_time_unix:
          type: integer
          title: Request Time Unix
          description: The date of the manual verification in Unix time.
        files:
          items:
            $ref: '#/components/schemas/ManualVerificationFileResponseModel'
          type: array
          title: Files
          description: The files of the manual verification.
      type: object
      required:
      - extra_text
      - request_time_unix
      - files
      title: ManualVerificationResponseModel
      example:
        extra_text: Please verify the voice is that of a female.
        files:
        - file_id: CwhRBWXzGAHq8TQ4Fs18
          file_name: file.mp3
          mime_type: audio/mpeg
          size_bytes: 1000000
          upload_date_unix: 1714204800
        request_time_unix: 1714204800
    SpeakerSeparationResponseModel:
      properties:
        voice_id:
          type: string
          title: Voice Id
          description: The ID of the voice.
        sample_id:
          type: string
          title: Sample Id
          description: The ID of the sample.
        status:
          type: string
          enum:
          - not_started
          - pending
          - completed
          - failed
          title: Status
          description: The status of the speaker separation.
        speakers:
          anyOf:
          - additionalProperties:
              $ref: '#/components/schemas/SpeakerResponseModel'
            type: object
          - type: 'null'
          title: Speakers
          description: The speakers of the sample.
        selected_speaker_ids:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Selected Speaker Ids
          description: The IDs of the selected speakers.
      type: object
      required:
      - voice_id
      - sample_id
      - status
      title: SpeakerSeparationResponseModel
      example:
        sample_id: DCwhRBWXzGAHq8TQ4Fs18
        status: not_started
        voice_id: DCwhRBWXzGAHq8TQ4Fs18
    VoiceSharingModerationCheckResponseModel:
      properties:
        date_checked_unix:
          anyOf:
          - type: integer
          - type: 'null'
          title: Date Checked Unix
          description: The date the moderation check was made in Unix time.
        name_value:
          anyOf:
          - type: string
          - type: 'null'
          title: Name Value
          description: The name value of the voice.
        name_check:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Name Check
          description: Whether the name check was successful.
        description_value:
          anyOf:
          - type: string
          - type: 'null'
          title: Description Value
          description: The description value of the voice.
        description_check:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Description Check
          description: Whether the description check was successful.
        sample_ids:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Sample Ids
          description: A list of sample IDs.
        sample_checks:
          anyOf:
          - items:
              type: number
            type: array
          - type: 'null'
          title: Sample Checks
          description: A list of sample checks.
        captcha_ids:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Captcha Ids
          description: A list of captcha IDs.
        captcha_checks:
          anyOf:
          - items:
              type: number
            type: array
          - type: 'null'
          title: Captcha Checks
          description: A list of CAPTCHA check values.
      type: object
      title: VoiceSharingModerationCheckResponseModel
      example:
        captcha_checks:
        - 0.95
        - 0.98
        captcha_ids:
        - captcha1
        - captcha2
        date_checked_unix: 1714204800
        description_check: true
        description_value: A female voice with a soft and friendly tone.
        name_check: true
        name_value: Rachel
        sample_checks:
        - 0.95
        - 0.98
        sample_ids:
        - sample1
        - sample2
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    VoiceSettingsResponseModel:
      properties:
        stability:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Stability
          description: Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion.
          default: 0.5
        use_speaker_boost:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Use Speaker Boost
          description: This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.
          default: true
        similarity_boost:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Similarity Boost
          description: Determines how closely the AI should adhere to the original voice when attempting to replicate it.
          default: 0.75
        style:
          anyOf:
          - type: number
          - type: 'null'
          title: Style
          description: Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0.
          default: 0.0
        speed:
          anyOf:
          - type: number
          - type: 'null'
          title: Speed
          description: Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up.
          default: 1.0
      type: object
      title: VoiceSettingsResponseModel
      example:
        similarity_boost: 1.0
        speed: 1.0
        stability: 1.0
        style: 0.0
        use_speaker_boost: true
    VoiceVerificationResponseModel:
      properties:
        requires_verification:
          type: boolean
          title: Requires Verification
          description: Whether the voice requires verification.
        is_verified:
          type: boolean
          title: Is Verified
          description: Whether the voice has been verified.
        verification_failures:
          items:
            type: string
          type: array
          title: Verification Failures
          description: List of verification failures.
        verification_attempts_count:
          type: integer
          title: Verification Attempts Count
          description: The number of verification attempts.
        language:
          anyOf:
          - type: string
          - type: 'null'
          title: Language
          description: The language of the voice.
        verification_attempts:
          anyOf:
          - items:
              $ref: '#/components/schemas/VerificationAttemptResponseModel'
            type: array
          - type: 'null'
          title: Verification Attempts
          description: Number of times a verification was attempted.
      type: object
      required:
      - requires_verification
      - is_verified
      - verification_failures
      - verification_attempts_count
      title: VoiceVerificationResponseModel
      example:
        is_verified: true
        language: en
        requires_verification: false
        verification_attempts:
        - accepted: true
          date_unix: 1714204800
          levenshtein_distance: 2
          recording:
            mime_type: audio/mpeg
            recording_id: CwhRBWXzGAHq8TQ4Fs17
            size_bytes: 1000000
            transcription: Hello, how are you?
            upload_date_unix: 1714204800
          similarity: 0.95
          text: Hello, how are you?
        verification_attempts_count: 0
        verification_failures: []
    SpeakerResponseModel:
      properties:
        speaker_id:
          type: string
          title: Speaker Id
          description: The ID of the speaker.
        duration_secs:
          type: number
          title: Duration Secs
          description: The duration of the speaker segment in seconds.
        utterances:
          anyOf:
          - items:
              $ref: '#/components/schemas/UtteranceResponseModel'
            type: array
          - type: 'null'
          title: Utterances
          description: The utterances of the speaker.
      type: object
      required:
      - speaker_id
      - duration_secs
      title: SpeakerResponseModel
      example:
        duration_secs: 5.0
        speaker_id: DCwhRBWXzGAHq8TQ4Fs18
    VoiceResponseModel:
      properties:
        voice_id:
          type: string
          title: Voice Id
          description: The ID of the voice.
        name:
          type: string
          title: Name
          description: The name of the voice.
        samples:
          anyOf:
          - items:
              $ref: '#/components/schemas/SampleResponseModel'
            type: array
          - type: 'null'
          title: Samples
          description: List of samples associated with the voice.
        category:
          type: string
          enum:
          - generated
          - cloned
          - premade
          - professional
          - famous
          - high_quality
          title: Category
          description: The category of the voice.
        fine_tuning:
          anyOf:
          - $ref: '#/components/schemas/FineTuningResponseModel'
          - type: 'null'
          description: Fine-tuning information for the voice.
        labels:
          additionalProperties:
            type: string
          type: object
          title: Labels
          description: Labels associated with the voice.
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          description: The description of the voice.
        preview_url:
          anyOf:
          - type: string
          - type: 'null'
          title: Preview Url
          description: The preview URL of the voice.
        available_for_tiers:
          items:
            type: string
          type: array
          title: Available For Tiers
          description: The tiers the voice is available for.
        settings:
          anyOf:
          - $ref: '#/components/schemas/VoiceSettingsResponseModel'
          - type: 'null'
          description: The settings of the voice.
        sharing:
          anyOf:
          - $ref: '#/components/schemas/VoiceSharingResponseModel'
          - type: 'null'
          description: The sharing information of the voice.
        high_quality_base_model_ids:
          items:
            type: string
          type: array
          title: High Quality Base Model Ids
          description: The base model IDs for high-quality voices.
        verified_languages:
          anyOf:
          - items:
              $ref: '#/components/schemas/VerifiedVoiceLanguageResponseModel'
            type: array
          - type: 'null'
          title: Verified Languages
          description: The verified languages of the voice.
        collection_ids:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Collection Ids
          description: The IDs of collections this voice belongs to.
        safety_control:
          anyOf:
          - type: string
            enum:
            - NONE
            - BAN
            - CAPTCHA
            - ENTERPRISE_BAN
            - ENTERPRISE_CAPTCHA
          - type: 'null'
          title: Safety Control
          description: The safety controls of the voice.
        voice_verification:
          anyOf:
          - $ref: '#/components/schemas/VoiceVerificationResponseModel'
          - type: 'null'
          description: The voice verification of the voice.
        permission_on_resource:
          anyOf:
          - type: string
          - type: 'null'
          title: Permission On Resource
          description: The permission on the resource of the voice.
        is_owner:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Is Owner
          description: Whether the voice is owned by the user.
        is_legacy:
          type: boolean
          title: Is Legacy
          description: Whether the voice is legacy.
          default: false
        is_mixed:
          type: boolean
          title: Is Mixed
          description: Whether the voice is mixed.
          default: false
        favorited_at_unix:
          anyOf:
          - type: integer
          - type: 'null'
          title: Favorited At Unix
          description: Timestamp when the voice was marked as favorite in Unix time.
        created_at_unix:
          anyOf:
          - type: integer
          - type: 'null'
          title: Created At Unix
          description: The creation time of the voice in Unix time.
        is_bookmarked:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Is Bookmarked
          description: Whether the voice is bookmarked by the current user. Only relevant for community (library-copied) voices.
        recording_quality:
          anyOf:
          - type: string
            enum:
            - studio
            - good
            - ok
            - poor
            - bad
          - type: 'null'
          title: Recording Quality
          description: The recording quality of the voice as determined by the review pipeline.
        labelling_status:
          anyOf:
          - type: string
            enum:
            - in_review
            - review_complete
          - type: 'null'
          title: Labelling Status
          description: The review pipeline status of the voice.
        recording_quality_reason:
          anyOf:
          - type: string
          - type: 'null'
          title: Recording Quality Reason
          description: The reason for the recording quality assessment, as determined by the review pipeline.
      type: object
      required:
      - voice_id
      - name
      - category
      - labels
      - available_for_tiers
      - high_quality_base_model_ids
      title: VoiceResponseModel
      example:
        available_for_tiers:
        - creator
        - enterprise
        category: professional
        description: A warm, expressive voice with a touch of humor.
        fine_tuning:
          is_allowed_to_fine_tune: true
          manual_verification_requested: false
          state:
            eleven_multilingual_v2: fine_tuned
          verification_attempts_count: 2
          verification_failures: []
        high_quality_base_model_ids:
        - eleven_v2_flash
        - eleven_flash_v2
        - eleven_turbo_v2_5
        - eleven_multilingual_v2
        - eleven_v2_5_flash
        - eleven_flash_v2_5
        - eleven_turbo_v2
        is_legacy: false
        is_mixed: false
        is_owner: false
        labels:
          accent: American
          age: middle-aged
          description: expressive
          gender: female
          use_case: social media
        name: Rachel
        preview_url: https://storage.googleapis.com/eleven-public-prod/premade/voices/9BWtsMINqrJLrRacOk9x/405766b8-1f4e-4d3c-aba1-6f25333823ec.mp3
        settings:
          similarity_boost: 1.0
          speed: 1.0
          stability: 1.0
          style: 0.0
          use_speaker_boost: true
        sharing:
          category: professional
          cloned_by_count: 50
          date_unix: 1714204800
          description: A female voice with a soft and friendly tone.
          disable_at_unix: 1714204800
          enabled_in_library: true
          featured: true
          financial_rewards_enabled: true
          free_users_allowed: true
          history_item_sample_id: DCwhRBWXzGAHq8TQ4Fs18
          labels:
            accent: American
            gender: female
          liked_by_count: 100
          live_moderation_enabled: true
          moderation_check:
            captcha_checks:
            - 0.95
            - 0.98
            captcha_ids:
            - captcha1
            - captcha2
            date_checked_unix: 1714204800
            description_check: true
            description_value: A female voice with a soft and friendly tone.
            name_check: true
            name_value: Rachel
            sample_checks:
            - 0.95
            - 0.98
            sample_ids:
            - sample1
            - sample2
          name: Rachel
          notice_period: 30
          original_voice_id: DCwhRBWXzGAHq8TQ4Fs18
          public_owner_id: DCwhRBWXzGAHq8TQ4Fs18
          rate: 0.05
          reader_app_enabled: true
          reader_restricted_on:
          - resource_id: FCwhRBWXzGAHq8TQ4Fs18
            resource_type: read
          review_status: allowed
          status: enabled
          voice_mixing_allowed: false
          whitelisted_emails:
          - example@example.com
        verified_languages:
        - accent: american
          language: en
          locale: en-US
          model_id: eleven_multilingual_v2
          preview_url: https://storage.googleapis.com/eleven-public-prod/premade/voices/9BWtsMINqrJLrRacOk9x/405766b8-1f4e-4d3c-aba1-6f25333823ec.mp3
        voice_id: 21m00Tcm4TlvDq8ikWAM
        voice_verification:
          is_verified: true
          language: en
          requires_verification: false
          verification_attempts:
          - accepted: true
            date_unix: 1714204800
            levenshtein_distance: 2
            recording:
              mime_type: audio/mpeg
              recording_id: CwhRBWXzGAHq8TQ4Fs17
              size_bytes: 1000000
              transcription: Hello, how are you?
              upload_date_unix: 1714204800
            similarity: 0.95
            text: Hello, how are you?
          verification_attempts_count: 0
          verification_failures: []
    FineTuningResponseModel:
      properties:
        is_allowed_to_fine_tune:
          type: boolean
          title: Is Allowed To Fine Tune
          description: Whether the user is allowed to fine-tune the voice.
        state:
          additionalProperties:
            type: string
            enum:
            - not_started
            - queued
            - fine_tuning
            - fine_tuned
            - failed
            - delayed
          type: object
          title: State
          description: The state of the fine-tuning process for each model.
        verification_failures:
          items:
            type: string
          type: array
          title: Verification Failures
          description: List of verification failures in the fine-tuning process.
        verification_attempts_count:
          type: integer
          title: Verification Attempts Count
          description: The number of verification attempts in the fine-tuning process.
        manual_verification_requested:
          type: boolean
          title: Manual Verification Requested
          description: Whether a manual verification was requested for the fine-tuning process.
        language:
          anyOf:
          - type: string
          - type: 'null'
          title: Language
          description: The language of the fine-tuning process.
        progress:
          anyOf:
          - additionalProperties:
              type: number
            type: object
          - type: 'null'
          title: Progress
          description: The progress of the fine-tuning process.
        message:
          anyOf:
          - additionalProperties:
              type: string
            type: object
          - type: 'null'
          title: Message
          description: The message of the fine-tuning process.
        dataset_duration_seconds:
          anyOf:
          - type: number
          - type: 'null'
          title: Dataset Duration Seconds
          description: The duration of the dataset in seconds.
        verification_attempts:
          anyOf:
          - items:
              $ref: '#/components/schemas/VerificationAttemptResponseModel'
            type: array
          - type: 'null'
          title: Verification Attempts
          description: The number of verification attempts.
        slice_ids:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Slice Ids
          description: List of slice IDs.
        manual_verification:
          anyOf:
          - $ref: '#/components/schemas/ManualVerificationResponseModel'
          - type: 'null'
          description: The manual verification of the fine-tuning process.
        max_verification_attempts:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Verification Attempts
          description: The maximum number of verification attempts.
        next_max_verification_attempts_reset_unix_ms:
          anyOf:
          - type: integer
          - type: 'null'
          title: Next Max Verification Attempts Reset Unix Ms
          description: The next maximum verification attempts reset time in Unix milliseconds.
      type: object
      required:
      - is_allowed_to_fine_tune
      - state
      - verification_failures
      - verification_attempts_count
      - manual_verification_requested
      title: FineTuningResponseModel
      example:
        is_allowed_to_fine_tune: true
        manual_verification_requested: false
        state:
          eleven_multilingual_v2: fine_tuned
        verification_attempts_count: 2
        verification_failures: []
    VerificationAttemptResponseModel:
      properties:
        text:
          type: string
          title: Text
          description: The text of the verification attempt.
        date_unix:
          type: integer
          title: Date Unix
          description: The date of the verification attempt in Unix time.
        accepted:
          type: boolean
          title: Accepted
          description: Whether the verification attempt was accepted.
        similarity:
          type: number
          title: Similarity
          description: The similarity of the verification attempt.
        levenshtein_distance:
          type: number
          title: Levenshtein Distance
          description: The Levenshtein distance of the verification attempt.
        recording:
          anyOf:
          - $ref: '#/components/schemas/RecordingResponseModel'
          - type: 'null'
          description: The recording of the verification attempt.
      type: object
      required:
      - text
      - date_unix
      - accepted
      - similarity
      - levenshtein_distance
      title: VerificationAttemptResponseModel
      example:
        accepted: true
        date_unix: 1714204800
        levenshtein_distance: 2
        recording:
          mime_type: audio/mpeg
          recording_id: CwhRBWXzGAHq8TQ4Fs17
          size_bytes: 1000000
          transcription: Hello, how are you?
          upload_date_unix: 1714204800
        similarity: 0.95
        text: Hello, how are you?
    VoicePreviewsResponseModel:
      properties:
        previews:
          items:
            $ref: '#/components/schemas/VoicePreviewResponseModel'
          type: array
          title: Previews
          description: The previews of the generated voices.
        text:
          type: string
          title: Text
          description: The text used to preview the voices.
      type: object
      required:
      - previews
      - text
      title: VoicePreviewsResponseModel
    VoiceDesignRequestModel:
      properties:
        voice_description:
          type: string
          maxLength: 1000
          minLength: 20
          title: Voice Description
          description: Description to use for the created voice.
          examples:
          - A sassy squeaky mouse
        model_id:
          type: string
          enum:
          - eleven_multilingual_ttv_v2
          - eleven_ttv_v3
          title: Model Id
          description: 'Model to use for the voice generation. Possible values: eleven_multilingual_ttv_v2, eleven_ttv_v3.'
          default: eleven_multilingual_ttv_v2
          examples:
          - eleven_multilingual_ttv_v2
        text:
          anyOf:
          - type: string
            maxLength: 1000
            minLength: 100
          - type: 'null'
          title: Text
          description: Text to generate, text length has to be between 100 and 1000.
          examples:
          - Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.
        auto_generate_text:
          type: boolean
          title: Auto Generate Text
          description: Whether to automatically generate a text suitable for the voice description.
          default: false
        loudness:
          type: number
          maximum: 1.0
          minimum: -1.0
          title: Loudness
          description: Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.
          default: 0.5
          examples:
          - 0.5
        seed:
          anyOf:
          - type: integer
            maximum: 2147483647.0
            minimum: 0.0
          - type: 'null'
          title: Seed
          description: Random number that controls the voice generation. Same seed with same inputs produces same voice.
          examples:
          - 11
        guidance_scale:
          type: number
          maximum: 100.0
          minimum: 0.0
          title: Guidance Scale
          description: Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.
          default: 5
          examples:
          - 5
        stream_previews:
          type: boolean
          title: Stream Previews
          description: Determines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint.
          default: false
          examples:
          - true
        should_enhance:
          type: boolean
          title: Should Enhance
          description: Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False
          default: false
          examples:
          - true
        remixing_session_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Remixing Session Id
          description: The remixing session id.
          examples:
          - '123'
        remixing_session_iteration_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Remixing Session Iteration Id
          description: The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.
          examples:
          - '123'
        quality:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: -1.0
          - type: 'null'
          title: Quality
          description: Higher quality results in better voice output but less variety.
          examples:
          - 0.9
        reference_audio_base64:
          anyOf:
          - type: string
          - type: 'null'
          title: Reference Audio Base64
          description: Reference audio to use for the voice generation. The audio should be base64 encoded. Only supported when using the  eleven_ttv_v3 model.
        prompt_strength:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Prompt Strength
          description: Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model.
          examples:
          - 0.25
      type: object
      required:
      - voice_description
      title: VoiceDesignRequestModel
    ReaderResourceResponseModel:
      properties:
        resource_type:
          type: string
          enum:
          - read
          - collection
          title: Resource Type
          description: The type of resource.
        resource_id:
          type: string
          title: Resource Id
          description: The ID of the resource.
      type: object
      required:
      - resource_type
      - resource_id
      title: ReaderResourceResponseModel
      example:
        resource_id: FCwhRBWXzGAHq8TQ4Fs18
        resource_type: read
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    RecordingResponseModel:
      properties:
        recording_id:
          type: string
          title: Recording Id
          description: The ID of the recording.
        mime_type:
          type: string
          title: Mime Type
          description: The MIME type of the recording.
        size_bytes:
          type: integer
          title: Size Bytes
          description: The size of the recording in bytes.
        upload_date_unix:
          type: integer
          title: Upload Date Unix
          description: The date of the recording in Unix time.
        transcription:
          type: string
          title: Transcription
          description: The transcription of the recording.
      type: object
      required:
      - recording_id
      - mime_type
      - size_bytes
      - upload_date_unix
      - transcription
      title: RecordingResponseModel
      example:
        mime_type: audio/mpeg
        recording_id: CwhRBWXzGAHq8TQ4Fs17
        size_bytes: 1000000
        transcription: Hello, how are you?
        upload_date_unix: 1714204800
    UtteranceResponseModel:
      properties:
        start:
          type: number
          title: Start
          description: The start time of the utterance in seconds.
        end:
          type: number
          title: End
          description: The end time of the utterance in seconds.
      type: object
      required:
      - start
      - end
      title: UtteranceResponseModel
      example:
        end: 1.0
        start: 0.0
    VerifiedVoiceLanguageResponseModel:
      properties:
        language:
          type: string
          title: Language
          description: The language of the voice.
        model_id:
          type: string
          title: Model Id
          description: The voice's model ID.
        accent:
          anyOf:
          - type: string
          - type: 'null'
          title: Accent
          description: The voice's accent, if applicable.
        locale:
          anyOf:
          - type: string
          - type: 'null'
          title: Locale
          description: The voice's locale, if applicable.
        preview_url:
          anyOf:
          - type: string
          - type: 'null'
          title: Preview Url
          description: The voice's preview URL, if applicable.
      type: object
      required:
      - language
      - model_id
      title: VerifiedVoiceLanguageResponseModel
      example:
        accent: American
        language: en
        model_id: eleven_turbo_v2_5
    AllowedOutputFormats:
      type: string
      enum:
      - mp3_22050_32
      - mp3_24000_48
      - mp3_44100_32
      - mp3_44100_64
      - mp3_44100_96
      - mp3_44100_128
      - mp3_44100_192
      - pcm_8000
      - pcm_16000
      - pcm_22050
      - pcm_24000
      - pcm_32000
      - pcm_44100
      - pcm_48000
      - ulaw_8000
      - alaw_8000
      - opus_48000_32
      - opus_48000_64
      - opus_48000_96
      - opus_48000_128
      - opus_48000_192
    VoiceRemixRequestModel:
      properties:
        voice_description:
          type: string
          maxLength: 1000
          minLength: 5
          title: Voice Description
          description: Description of the changes to make to the voice.
          examples:
          - Make the voice have a higher pitch.
        text:
          anyOf:
          - type: string
            maxLength: 1000
            minLength: 100
          - type: 'null'
          title: Text
          description: Text to generate, text length has to be between 100 and 1000.
          examples:
          - Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.
        auto_generate_text:
          type: boolean
          title: Auto Generate Text
          description: Whether to automatically generate a text suitable for the voice description.
          default: false
        loudness:
          type: number
          maximum: 1.0
          minimum: -1.0
          title: Loudness
          description: Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.
          default: 0.5
          examples:
          - 0.5
        seed:
          anyOf:
          - type: integer
            maximum: 2147483647.0
            minimum: 0.0
          - type: 'null'
          title: Seed
          description: Random number that controls the voice generation. Same seed with same inputs produces same voice.
          examples:
          - 11
        guidance_scale:
          type: number
          maximum: 100.0
          minimum: 0.0
          title: Guidance Scale
          description: Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.
          default: 2
          examples:
          - 5
        stream_previews:
          type: boolean
          title: Stream Previews
          description: Determines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint.
          default: false
          examples:
          - true
        remixing_session_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Remixing Session Id
          description: The remixing session id.
          examples:
          - '123'
        remixing_session_iteration_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Remixing Session Iteration Id
          description: The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.
          examples:
          - '123'
        prompt_strength:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Prompt Strength
          description: Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model.
          examples:
          - 0.25
      type: object
      required:
      - voice_description
      title: VoiceRemixRequestModel
    VoiceSharingResponseModel:
      properties:
        status:
          type: string
          enum:
          - enabled
          - disabled
          - copied
          - copied_disabled
          title: Status
          description: The status of the voice sharing.
        history_item_sample_id:
          anyOf:
          - type: string
          - type: 'null'
          title: History Item Sample Id
          description: The sample ID of the history item.
        date_unix:
          type: integer
          title: Date Unix
          description: The date of the voice sharing in Unix time.
        whitelisted_emails:
          items:
            type: string
          type: array
          title: Whitelisted Emails
          description: A list of whitelisted emails.
        public_owner_id:
          type: string
          title: Public Owner Id
          description: The ID of the public owner.
        original_voice_id:
          type: string
          title: Original Voice Id
          description: The ID of the original voice.
        financial_rewards_enabled:
          type: boolean
          title: Financial Rewards Enabled
          description: Whether financial rewards are enabled.
        free_users_allowed:
          type: boolean
          title: Free Users Allowed
          description: Whether free users are allowed.
        live_moderation_enabled:
          type: boolean
          title: Live Moderation Enabled
          description: Whether live moderation is enabled.
        rate:
          anyOf:
          - type: number
          - type: 'null'
          title: Rate
          description: The rate of the voice sharing.
        fiat_rate:
          anyOf:
          - type: number
          - type: 'null'
          title: Fiat Rate
          description: The rate of the voice sharing in USD per 1000 credits.
        notice_period:
          type: integer
          title: Notice Period
          description: The notice period of the voice sharing.
        disable_at_unix:
          anyOf:
          - type: integer
          - type: 'null'
          title: Disable At Unix
          description: The date of the voice sharing in Unix time.
        voice_mixing_allowed:
          type: boolean
          title: Voice Mixing Allowed
          description: Whether voice mixing is allowed.
        featured:
          type: boolean
          title: Featured
          description: Whether the voice is featured.
        category:
          type: string
          enum:
          - generated
          - cloned
          - premade
          - professional
          - famous
          - high_quality
          title: Category
          description: The category of the voice.
        reader_app_enabled:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Reader App Enabled
          description: Whether the reader app is enabled.
        image_url:
          anyOf:
          - type: string
          - type: 'null'
          title: Image Url
          description: The image URL of the voice.
        ban_reason:
          anyOf:
          - type: string
          - type: 'null'
          title: Ban Reason
          description: The ban reason of the voice.
        liked_by_count:
          type: integer
          title: Liked By Count
          description: The number of likes on the voice.
        cloned_by_count:
          type: integer
          title: Cloned By Count
          description: The number of clones on the voice.
        name:
          type: string
          title: Name
          description: The name of the voice.
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
          description: The description of the voice.
        labels:
          additionalProperties:
            type: string
          type: object
          title: Labels
          description: The labels of the voice.
        review_status:
          type: string
          enum:
          - not_requested
          - pending
          - declined
          - allowed
          - allowed_with_changes
          title: Review Status
          description: The review status of the voice.
        review_message:
          anyOf:
          - type: string
          - type: 'null'
          title: Review Message
          description: The review message of the voice.
        enabled_in_library:
          type: boolean
          title: Enabled In Library
          description: Whether the voice is enabled in the library.
        instagram_username:
          anyOf:
          - type: string
          - type: 'null'
          title: Instagram Username
          description: The Instagram username of the voice.
        twitter_username:
          anyOf:
          - type: string
          - type: 'null'
          title: Twitter Username
          description: The Twitter/X username of the voice.
        youtube_username:
          anyOf:
          - type: string
          - type: 'null'
          title: Youtube Username
          description: The YouTube username of the voice.
        tiktok_username:
          anyOf:
          - type: string
          - type: 'null'
          title: Tiktok Username
          description: The TikTok username of the voice.
        moderation_check:
          anyOf:
          - $ref: '#/components/schemas/VoiceSharingModerationCheckResponseModel'
          - type: 'null'
          description: The moderation check of the voice.
        reader_restricted_on:
          anyOf:
          - items:
              $ref: '#/components/schemas/ReaderResourceResponseModel'
            type: array
          - type: 'null'
          title: Reader Restricted On
          description: The reader restricted on of the voice.
      type: object
      required:
      - status
      - date_unix
      - whitelisted_emails
      - public_owner_id
      - original_voice_id
      - financial_rewards_enabled
      - free_users_allowed
      - live_moderation_enabled
      - notice_period
      - voice_mixing_allowed
      - featured
      - category
      - liked_by_count
      - cloned_by_count
      - name
      - labels
      - review_status
      - enabled_in_library
      title: VoiceSharingResponseModel
      example:
        category: professional
        cloned_by_count: 50
        date_unix: 1714204800
        description: A female voice with a soft and friendly tone.
        disable_at_unix: 1714204800
        enabled_in_library: true
        featured: true
        financial_rewards_enabled: true
        free_users_allowed: true
        history_item_sample_id: DCwhRBWXzGAHq8TQ4Fs18
        labels:
          accent: American
          gender: female
        liked_by_count: 100
        live_moderation_enabled: true
        moderation_check:
          captcha_checks:
          - 0.95
          - 0.98
          captcha_ids:
          - captcha1
          - captcha2
          date_checked_unix: 1714204800
          description_check: true
          description_value: A female voice with a soft and friendly tone.
          name_check: true
          name_value: Rachel
          sample_checks:
          - 0.95
          - 0.98
          sample_ids:
          - sample1
          - sample2
        name: Rachel
        notice_period: 30
        original_voice_id: DCwhRBWXzGAHq8TQ4Fs18
        public_owner_id: DCwhRBWXzGAHq8TQ4Fs18
        rate: 0.05
        reader_app_enabled: true
        reader_restricted_on:
        - resource_id: FCwhRBWXzGAHq8TQ4Fs18
          resource_type: read
        review_status: allowed
        status: enabled
        voice_mixing_allowed: false
        whitelisted_emails:
        - example@example.com
    ManualVerificationFileResponseModel:
      properties:
        file_id:
          type: string
          title: File Id
          description: The ID of the file.
        file_name:
          type: string
          title: File Name
          description: The name of the file.
        mime_type:
          type: string
          title: Mime Type
          description: The MIME type of the file.
        size_bytes:
          type: integer
          title: Size Bytes
          description: The size of the file in bytes.
        upload_date_unix:
          type: integer
          title: Upload Date Unix
          description: The date of the file in Unix time.
      type: object
      required:
      - file_id
      - file_name
      - mime_type
      - size_bytes
      - upload_date_unix
      title: ManualVerificationFileResponseModel
      example:
        file_id: CwhRBWXzGAHq8TQ4Fs18
        file_name: file.mp3
        mime_type: audio/mpeg
        size_bytes: 1000000
        upload_date_unix: 1714204800
    VoicePreviewsRequestModel:
      properties:
        voice_description:
          type: string
          maxLength: 1000
          minLength: 20
          title: Voice Description
          description: Description to use for the created voice.
          examples:
          - A sassy squeaky mouse
        text:
          anyOf:
          - type: string
            maxLength: 1000
            minLength: 100
          - type: 'null'
          title: Text
          description: Text to generate, text length has to be between 100 and 1000.
          examples:
          - Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.
        auto_generate_text:
          type: boolean
          title: Auto Generate Text
          description: Whether to automatically generate a text suitable for the voice description.
          default: false
        loudness:
          type: number
          maximum: 1.0
          minimum: -1.0
          title: Loudness
          description: Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.
          default: 0.5
          examples:
          - 0.5
        quality:
          type: number
          maximum: 1.0
          minimum: -1.0
          title: Quality
          description: Higher quality results in better voice output but less variety.
          default: 0.9
          examples:
          - 0.9
        seed:
          anyOf:
          - type: integer
            maximum: 2147483647.0
            minimum: 0.0
          - type: 'null'
          title: Seed
          description: Random number that controls the voice generation. Same seed with same inputs produces same voice.
          examples:
          - 11
        guidance_scale:
          type: number
          maximum: 100.0
          minimum: 0.0
          title: Guidance Scale
          description: Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.
          default: 5
          examples:
          - 5
        should_enhance:
          type: boolean
          title: Should Enhance
          description: Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False
          default: false
          examples:
          - true
      type: object
      required:
      - voice_description
      title: VoicePreviewsRequestModel