> ## Documentation Index > Fetch the complete documentation index at: https://www.edenai.co/docs/llms.txt > Use this file to discover all available pages before exploring further. # Audio Transcriptions > OpenAI-compatible speech-to-text endpoint. Accepts either ``multipart/form-data`` (OpenAI SDK shape: a ``file`` upload plus text fields) or ``application/json`` (``file_id`` / ``file_url`` plus text fields). Content-Type drives dispatch. ## OpenAPI ````yaml https://api.edenai.run/v3/docs/openapi.json post /v3/audio/transcriptions openapi: 3.1.0 info: title: Eden AI API V3 version: 3.0.0 servers: - url: https://api.edenai.run description: Production server security: [] paths: /v3/audio/transcriptions: post: tags: - Audio summary: Audio Transcriptions description: >- OpenAI-compatible speech-to-text endpoint. Accepts either ``multipart/form-data`` (OpenAI SDK shape: a ``file`` upload plus text fields) or ``application/json`` (``file_id`` / ``file_url`` plus text fields). Content-Type drives dispatch. operationId: audio_transcriptions_v3_audio_transcriptions_post requestBody: content: application/json: schema: properties: routing: anyOf: - $ref: '#/components/schemas/ProviderRoutingPreferences' - type: 'null' description: >- How to pick between the providers that serve the requested model. Applies only when `model` is a model name with no provider prefix (e.g. 'gpt-5.5'); ignored for a concrete 'provider/model' id, which already names its provider. This does not choose the model — for that see `router_candidates` with model='@edenai'. model: type: string title: Model description: provider/model, e.g. 'openai/whisper-1' language: anyOf: - type: string - type: 'null' title: Language description: >- ISO-639-1 language code of the input audio (e.g. 'en'). Omit to let the provider auto-detect where supported. prompt: anyOf: - type: string - type: 'null' title: Prompt description: >- Optional text to guide the model's style or continue a prior audio segment's context. response_format: anyOf: - type: string - type: 'null' title: Response Format description: >- Transcript format: 'json', 'text', 'srt', 'verbose_json', or 'vtt'. Provider support varies; forwarded as-is. timestamp_granularities: anyOf: - items: type: string type: array - type: 'null' title: Timestamp Granularities description: >- Timestamp granularities to populate with 'verbose_json' (['word'] and/or ['segment']). temperature: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Temperature description: Sampling temperature between 0 and 1. user: anyOf: - type: string - type: 'null' title: User description: End-user identifier for abuse tracking. file_id: anyOf: - type: string - type: 'null' title: File Id description: Id of a file previously uploaded to Eden AI. file_url: anyOf: - type: string - type: 'null' title: File Url description: An https URL or a base64 data URL pointing at the audio. type: object required: - model title: TranscriptionJsonBody description: >- JSON request body, references the audio by ``file_id`` or ``file_url``. Exactly one of ``file_id`` (an Eden upload id) or ``file_url`` (an https URL or a ``data:audio/...;base64,...`` URL) must be set. required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/TranscriptionResponse' security: - AuthBearer: [] components: schemas: ProviderRoutingPreferences: properties: sort: anyOf: - type: string enum: - cost - speed - latency - exact - type: 'null' title: Sort description: >- What to optimise for when several providers serve the requested model. 'cost' (default) picks the cheapest for this request's shape; 'speed' the highest tokens/second; 'latency' the fastest to first token; 'exact' the most reliable at producing well-formed tool calls / structured output. Health is always a filter first — no mode will route you to a failing provider. Can also be written as a model suffix, e.g. 'gpt-5.5:speed'. allow_fallbacks: type: boolean title: Allow Fallbacks description: >- Whether other providers of the same model may be tried when the chosen one fails. Set false to pin the request to the single best provider: it then fails rather than silently moving to another seller. useful when a cache-warm prompt would cold-miss elsewhere. This governs PROVIDERS of the requested model only; models you list in `fallbacks` are your own choice and are always kept. default: true allowed_providers: anyOf: - items: type: string type: array - type: 'null' title: Allowed Providers description: >- Restrict routing to these providers, e.g. ['openai', 'anthropic']. Only providers that serve the requested model are considered, so an entry that does not sell it is simply inert. If none of them do, the request fails rather than falling back to a provider you excluded. Case-insensitive. Applies to routed providers only. a concrete 'provider/model' you named in `fallbacks` is your own choice and is kept. type: object title: ProviderRoutingPreferences description: >- How to choose between SELLERS of one model — not which model to use. Only meaningful when `model` is a canonical name (`gpt-5.5`) rather than a concrete `provider/model` — with a concrete id there is nothing to choose between. For choosing the MODEL itself see ``router_candidates`` and ``model="@edenai"``, which is a different router. TranscriptionResponse: properties: cost: anyOf: - type: number - type: 'null' title: Cost provider: anyOf: - type: string - type: 'null' title: Provider text: anyOf: - type: string - type: 'null' title: Text usage: anyOf: - additionalProperties: true type: object - type: 'null' title: Usage additionalProperties: true type: object title: TranscriptionResponse description: >- OpenAI-compatible transcription response, plus Eden ``cost`` / ``provider``. The provider's full transcript payload passes through — ``text`` plus any ``language``, ``duration``, ``words``, and ``segments`` the provider returns — alongside the Eden-added ``cost`` and ``provider`` fields. securitySchemes: AuthBearer: type: http scheme: bearer ````