FIfish
OpenAPI v1

Speech to Text

Changed on
post/v1/asr

Request

  • Base URL
    https://api.fish.audio
  • URL
    https://api.fish.audio/v1/asr
  • Auth
    HTTP bearer

Headers

model'transcribe-1' | 'transcribe-1-pro'

Specify which speech-to-text model to use.

Request body multipart/form-data

audiostring binary required

Audio file to be converted to text

languagestring nullable

Optional hint. The language is auto-detected regardless; the detected language is returned as language_code.

ignore_timestampsboolean

Whether to return precise timestamps in the text, this will increase the latency in audio shorter than 30 seconds

Response

Request fulfilled, document follows

textstring required
durationnumber required

Duration of the audio in seconds

language_codestring nullable

Detected language as an ISO 639-1 code (e.g. en, ja). Omitted if no language is detected.

languagestring nullable

Detected language name (e.g. English). For display only; use language_code in code.

Changes

  • 42ac421f7a12Revision changes
    • breaking

      removed the media type application/json from the request body

    • info

      added the new optional header request parameter model

    • info

      added the media type multipart/form-data to the request body

    • info

      added the non-success response with the status

    • info

      removed the non-success 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