STT

Create transcription

Changed on

Transcribes audio into text. Accepts base64-encoded audio input as JSON, an OpenAI-style multipart/form-data file upload, or a URL the provider downloads directly, and returns the transcribed text.

post/audio/transcriptions

Request

  • Base URL: https://openrouter.ai/api/v1
  • URL: https://openrouter.ai/api/v1/audio/transcriptions
  • Auth: HTTP bearer

Request body

diarizeboolean

Label each word with the speaker who said it. Speaker labels are returned on the words array (speaker, speaker_label), so response_format must be "verbose_json" (a "json" request is rejected with a 400) and word timestamps are included even when timestamp_granularities omits "word". Only supported by some providers; the request is rejected with a 400 when the selected model cannot diarize. Providers may charge extra.

keytermsstring[]

Domain terms, names, or phrases to bias recognition toward. Only supported by some providers; the request is rejected with a 400 when the selected model cannot use keyterms. Providers may cap the number of terms or characters per term and may charge extra.

languagestring

ISO-639-1 language code (e.g., "en", "ja"). Auto-detected if omitted.

modelstring required

STT model identifier

response_format'json' | 'verbose_json'

Output format. "json" (default) returns { text, usage }. "verbose_json" additionally returns task, language, duration, and segment-level timestamps; only supported by OpenAI-compatible providers.

session_idstring

A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters.

temperaturenumber double

Sampling temperature for transcription

timestamp_granularitiesSTTTimestampGranularity[]

Timestamp detail levels to include when response_format is "verbose_json". "segment" returns segment-level timestamps; "word" additionally returns word-level timestamps in the words array. Ignored unless response_format is "verbose_json".

userstring

A unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider.

Example request

{
  "input_audio": {
    "data": "UklGRiQA...",
    "format": "wav"
  },
  "language": "en",
  "model": "openai/whisper-large-v3"
}

Response

Transcription result

confidencenumber double

Provider confidence for the whole transcript from 0 to 1, present when response_format is verbose_json and the provider scores the full transcript

durationnumber double

Duration of the input audio in seconds, present when response_format is verbose_json

languagestring

Detected or forced language, present when response_format is verbose_json

language_confidencenumber double

Provider confidence in the detected language from 0 to 1, present when response_format is verbose_json and the provider scores language detection

taskstring

The task performed, present when response_format is verbose_json

textstring required

The transcribed text

Example response

{
  "text": "Hello, this is a test of OpenAI speech-to-text transcription.",
  "usage": {
    "cost": 0.000508,
    "input_tokens": 83,
    "output_tokens": 30,
    "seconds": 9.2,
    "total_tokens": 113
  }
}

Changes

  • 0020e8ddebdaRevision changes
    • info

      added the new optional request property / (media type: application/json)

    • info

      added the new optional request property / (media type: application/json)

  • 68a12e66c7faRevision changes
    • breaking

      the request property type changed from object to no type (media type: application/json)

    • warning

      removed the request property / (media type: application/json)

    • warning

      removed the request property / (media type: application/json)

    • info

      added the new optional request property (media type: application/json)

    • info

      added the new optional request property (media type: multipart/form-data)

    • info

      added the new optional request property (media type: application/json)

    • info

      added the new optional request property (media type: multipart/form-data)

    • info

      added the new optional request property (media type: multipart/form-data)

    • info

      added the new optional request property // (media type: application/json)

    • info

      added the new optional request property (media type: multipart/form-data)

    • info

      added to the request property anyOf list (media type: application/json)

    • info

      the request property became optional (media type: multipart/form-data)

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status