Transcribes audio into the input language.

POST

/audio/transcriptions

Authorizations

• ApiKeyAuth

Request Body ^required

object

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.

string format: binary

model

required

Any of:

string

string

string

string

Allowed values: whisper-1

language

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

string

prompt

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

string

response_format

The format of the output, in one of these options: json, text, srt, verbose_json, or vtt.

string

default: json

Allowed values: json text srt verbose_json vtt

temperature

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.

number

timestamp_granularities[]

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.

Array<string>

default: segment

Allowed values: word segment

Responses

200

OK

One of:

object

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

object

text

required

The transcribed text.

string

object

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

object

language

required

The language of the input audio.

string

duration

required

The duration of the input audio.

string

text

required

The transcribed text.

string

words

Extracted words and their corresponding timestamps.

Array<object>

object

word

required

The text content of the word.

string

start

required

Start time of the word in seconds.

number format: float

end

required

End time of the word in seconds.

number format: float

segments

Segments of the transcribed text and their corresponding details.

Array<object>

object

id

required

Unique identifier of the segment.

integer

seek

required

Seek offset of the segment.

integer

start

required

Start time of the segment in seconds.

number format: float

end

required

End time of the segment in seconds.

number format: float

text

required

Text content of the segment.

string

tokens

required

Array of token IDs for the text content.

Array<integer>

temperature

required

Temperature parameter used for generating the segment.

number format: float

avg_logprob

required

Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.

number format: float

compression_ratio

required

Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.

number format: float

no_speech_prob

required

Probability of no speech in the segment. If the value is higher than 1.0 and the avg_logprob is below -1, consider this segment silent.

number format: float