OpenAI API (unofficial showcase)
POST/audio/transcriptions

Create an audio transcription

Transcribes an audio file and returns the transcript in a selected format or as a stream of transcript events. Provide the audio file and model, then use options such as language, prompt, or timestamp_granularities to guide or shape the output. Use multipart form data and include enough file metadata for the audio format to be identified.

  • IdempotentThe SDK sends Idempotency-Key, so a retried request is only applied once.

14 body fields

Multipart form data containing an audio file, model selection, and optional transcription settings. file and model are required.

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
Set to `true` to receive transcription events as server-sent events. Defaults to `false` when omitted.
Default:false
chunking_strategystring | objectoptional
Controls how the audio is divided into chunks; supports automatic chunking or a server VAD configuration.
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`.

9 status codes
200Returns a transcription object, plain text, or a stream of transcript events, depending on the requested format and streaming options.
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.
400Returned when the audio input or request parameters are invalid.
errorobjectrequired
401Returned when the API key is missing or revoked, or the client IP is not authorized.
errorobjectrequired
403Returned when organization policy blocks access to a personal API organization.
413Returned when the audio request exceeds the supported size limit.
errorobjectrequired
429Returned when the request is rejected because a rate limit was exceeded.

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
500Returned when the audio could not be processed.
errorobjectrequired
502Returned when the upstream audio service connection fails.
errorobjectrequired
503Returned when the service is temporarily unavailable.

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 400 is returned for invalid audio input or request parameters; a 401 indicates a missing or revoked API key or an unauthorized client IP; a 403 indicates organization policy blocks access; and a 413 indicates the request exceeds the supported size limit. A 429 indicates a rate limit was exceeded, a 500 indicates the audio could not be processed, a 502 indicates an upstream audio service connection failure, and a 503 indicates temporary service unavailability. file and model are required; response_format must be supported by the selected model, temperature must be between 0 and 1, timestamp_granularities requires verbose_json, and speaker name and reference lists accept at most 4 items each.