POST
/
audio
/
transcriptions
Create transcription
curl --request POST \
  --url https://api.openai.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form model=gpt-4o-transcribe \
  --form 'language=<string>' \
  --form 'prompt=<string>' \
  --form response_format=json \
  --form temperature=0 \
  --form 'include[]=[]' \
  --form 'timestamp_granularities[]=segment' \
  --form stream=false \
  --form file=@example-file
{
  "text": "<string>"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
​
file
file
required

The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

​
model
required

ID of the model to use. The options are gpt-4o-transcribe, gpt-4o-mini-transcribe, and whisper-1 (which is powered by our open source Whisper V2 model).

Example:

"gpt-4o-transcribe"

​
language
string

The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

​
prompt
string

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

​
response_format
enum<string>
default:json

The format of the output, in one of these options: json, text, srt, verbose_json, or vtt. For gpt-4o-transcribe and gpt-4o-mini-transcribe, the only supported format is json.

Available options:
json,
text,
srt,
verbose_json,
vtt
​
temperature
number
default:0

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 to automatically increase the temperature until certain thresholds are hit.

​
include[]
enum<string>[]

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 and gpt-4o-mini-transcribe.

​
timestamp_granularities[]
enum<string>[]

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.

​
stream
boolean | null
default:false

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section of the Speech-to-Text guide for more information.

Note: Streaming is not supported for the whisper-1 model and will be ignored.

Response

OK

Represents a transcription response returned by model, based on the provided input.

​
text
string
required

The transcribed text.