For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
A list of keyterms to bias the transcription towards. The keyterms are words or phrases you want the model to recognise more accurately. The number of keyterms cannot exceed 1000. The length of each keyterm must be less than 50 characters. Keyterms can contain at most 5 words (after normalisation). For example ["hello", "world", "technical term"]. The following characters are not supported: `<`, `>`, `{`, `}`, `[`, `]`, `\`. Usage of this parameter will incur an additional 20% surcharge on the base transcription cost. When more than 100 keyterms are provided, a minimum billable duration of 20 seconds applies per request.
响应
同步转录结果
SpeechToTextChunkResponseModelobject
Chunk-level detail of the transcription with timing information.
A list of keyterms to bias the transcription towards. The keyterms are words or phrases you want the model to recognise more accurately. The number of keyterms cannot exceed 1000. The length of each keyterm must be less than 50 characters. Keyterms can contain at most 5 words (after normalisation). For example [“hello”, “world”, “technical term”]. The following characters are not supported: <, >, {, }, [, ], \. Usage of this parameter will incur an additional 20% surcharge on the base transcription cost. When more than 100 keyterms are provided, a minimum billable duration of 20 seconds applies per request.