Sample - OpenAI API
POST/audio/transcriptions

Create an audio transcription

Transcribes an uploaded audio file into its input language. Supply file and model, then choose the output format, language guidance, timestamps, speaker references, or streaming behavior. A successful response contains a transcription object or streamed transcript events.

  • RetriesRetries up to 2×, 500ms backoff, 30s timeout.

14 body fields

Multipart form data containing the audio file, transcription model, language guidance, output settings, and optional speaker or streaming configuration.

filestringrequired
The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. The request must include enough format metadata for the file to be identified. We recommend an extension-bearing filename and an appropriate content type.
modelstringrequired
ID of the model to use. The options are `gpt-transcribe`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1` (which is powered by our open source Whisper V2 model), and `gpt-4o-transcribe-diarize`.
languagestringoptional
The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency.
languagesarray<string>optional
Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe`.
keywordsarray<string>optional
Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe`.
promptstringoptional
An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://developers.openai.com/api/docs/guides/speech-to-text#prompting) should match the audio language. This field is not supported when using `gpt-4o-transcribe-diarize`.
response_formatstringoptional
The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`. For `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and `diarized_json`, with `diarized_json` required to receive speaker annotations.
Allowed:jsontextsrtverbose_jsonvttdiarized_jsonDefault:json
temperaturenumberoptional
The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.
Default:0
includearray<string>optional
Additional information to include in the transcription response. `logprobs` will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. `logprobs` only works with response_format set to `json` and only with the models `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is not supported when using `gpt-4o-transcribe-diarize`.
timestamp_granularitiesarray<string>optional
The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. This option is not available for `gpt-4o-transcribe-diarize`.
Default:["segment"]
streambooleanoptional
Whether to stream transcription events as server-sent events. Defaults to false when omitted.
Default:false
chunking_strategystring | objectoptional
Controls audio chunking using the supported automatic or server VAD strategy, or set to null to disable it.
known_speaker_namesarray<string>optional
Optional list of speaker names that correspond to the audio samples provided in `known_speaker_references[]`. Each entry should be a short identifier (for example `customer` or `agent`). Up to 4 speakers are supported.
known_speaker_referencesarray<string>optional
Optional list of audio samples (as [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs)) that contain known speaker references matching `known_speaker_names[]`. Each sample must be between 2 and 10 seconds, and can use any of the same input audio formats supported by `file`.

3 status codes
200Returns a transcription object containing the transcript and any requested language, timing, speaker, log-probability, or usage data, or returns streamed transcription events.
textstringrequired
The transcribed text.
languagesarray<object>optional
The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected.
logprobsarray<object>optional
The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array.
usageobjectoptional
Token usage statistics for the request.
429Returned when the request was rejected because the rate limit was exceeded; reduce the request rate if a `slow_down` error is reported.

One documented failure

  • slow_down

    Your request rate increased too quickly. Please reduce the request rate and gradually increase it again.

    Traffic increased too quickly

errorobjectrequired
503Returned when the service is temporarily unavailable or the requested model is overloaded; retry after a brief delay.

One documented failure

  • server_is_overloaded

    The model is temporarily overloaded. Please retry your request after a brief delay.

    The requested model is temporarily overloaded

errorobjectrequired

Error handling

A 429 is returned when the request exceeds the rate limit, and a 503 is returned when the service or requested model is temporarily unavailable. file and model are required; languages must contain at least one item when supplied, known_speaker_names and known_speaker_references allow at most four items, and response_format must be one of the listed formats.