Skip to main content

Speech Translation: start task

POST 
/api/technology/speech-translation-whisper-enhanced

Start an Enhanced Speech Translation Built on Whisper task for a media file.

Features of Enhanced Speech Translation Built on Whisper​

  • Multi-channel audio files are supported.
  • Channel ID is included in individual translation segments.
  • The target language of the translation can be specified with the output_language query parameter.
  • Source language for translation of the whole media file can be forced with the source_language query parameter, otherwise it is detected automatically.
  • Language switching can be activated with the language_switching query parameter. With this feature, the technology automatically identifies the predominant language spoken within each thirty-second segment of the file and uses it as the source language for translating that particular segment.
  • The source_language and language_switching parameters are mutually exclusive.
  • A language explicitly set as the source_language must be licensed. Otherwise, an error is raised.
  • When the source_language is autodetected or language_switching is used, only licensed languages are considered as the source for the translation. In case the actually detected language is not licensed, the closest licensed language is used instead.

Request​

Responses​

Speech Translation task was accepted. Follow the Location header to poll for the task state.

Response Headers
    X-Location

    ⚠️ Deprecated - use Location header instead.

    Example: /api/technology/speech-translation-whisper-enhanced/123e4567-e89b-12d3-a456-426614174000
    Location

    A URL the client should poll for task state and result.

    Example: /api/technology/speech-translation-whisper-enhanced/123e4567-e89b-12d3-a456-426614174000