Whisper STT
[Core Function] OpenAI Whisper transcribes a single public audio URL into text via an async task. [Strengths] Multiple output formats (verbose_json with word/segment timestamps, plain text, SRT, VTT), optional language and prompt biasing. [Best For] Meeting notes, podcasts, captions, and batch audio-to-text. [Limitations] Do NOT use file upload; URL-only input (audio up to 25 MB). Prefer verbose_json when you need duration or timestamps. [Routing] Use whisper-1 for OpenAI Whisper quality with URL-based audio.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Public http(s) URL of the audio file (max 25 MB).
1^https?://ISO-639-1 language hint for transcription.
Optional text to guide the model's style or continue a previous segment.
Sampling temperature; higher values increase randomness.
0 <= x <= 1Output format. verbose_json recommended for duration and timestamps.
json, text, srt, verbose_json, vtt Timestamp detail levels. Requires response_format=verbose_json when non-empty.
word, segment Response
Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; the transcription result is returned on the task result.
Response object for asynchronous task submission.
Response code, 0 indicates success
0
Response message
"success"
Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; the transcription appears in result.resources. See Common API: Query Task Result.