openapi: 3.0.3 info: title: Gladia Control AudioToText 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: {} servers: - url: https://api.gladia.io/ description: Gladia API production URL tags: - name: AudioToText paths: /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 components: securitySchemes: x_gladia_key: type: apiKey in: header name: x-gladia-key description: Your personal Gladia API key