POST /v1/audio/transcriptions accepts the same request as OpenAI’s transcription endpoint and answers in the same shape. Point an OpenAI SDK, or any tool built for that API, at https://api.aircaps.com/v1 with your AirCaps API key.
It runs the same model as batch transcription and returns the same transcript. The request is answered when the transcript is finished.
Make a request
Request fields
Send a multipart form.
Other OpenAI fields, such as
prompt and temperature, are accepted and ignored.
Timestamps and speakers
Ask forverbose_json to get segments, word timestamps and speakers:
- Times are seconds from the start of the audio.
- A segment is one speaker’s turn. Overlapping speech produces overlapping segments.
speakeris a number andspeaker_labelits name (speaker_0,speaker_1, …), in order of first speech. They are consistent within one transcript only.usage.secondsis the audio’s duration, which is what you are billed for, at the A5S Async v1 price.
Limits and errors
- The request waits up to 120 seconds for the transcript. If it is not finished by then, the response is
504with the codetimeout; the transcript is canceled and you are not billed. For long recordings, use batch transcription, which has webhooks and polling. - Errors use the same JSON as the rest of the API: see Errors. Audio that can’t be read returns
400 invalid_audio. Idempotency-Key, webhooks andmetadataare not available on this endpoint. Speaker names, subtitles and transcript ids are part of batch transcription.- Your account’s data controls apply as they do to batch transcription.

