Skip to content

transcription_create_params

Classes:

Name Description
TranscriptionCreateParams

TranscriptionCreateParams

Attributes:

Name Type Description
file Required[FileTypes]

The audio file object (not file name) to transcribe, in one of these formats:
language str

The language of the input audio.
model Required[Union[str, Literal['whisper-1']]]

ID of the model to use.
prompt str

An optional text to guide the model's style or continue a previous audio
response_format Literal['json', 'text', 'srt', 'verbose_json', 'vtt']

The format of the transcript output, in one of these options: json, text,
temperature float

The sampling temperature, between 0 and 1.
timestamp_granularities List[Literal['word', 'segment']]

The timestamp granularities to populate for this transcription.

file instance-attribute 

file: Required[FileTypes]

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

language instance-attribute 

language: str

The language of the input audio.

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

model instance-attribute 

model: Required[Union[str, Literal['whisper-1']]]

ID of the model to use.

Only whisper-1 (which is powered by our open source Whisper V2 model) is currently available.

prompt instance-attribute 

prompt: str

An optional text to guide the model's style or continue a previous audio segment.

The prompt should match the audio language.

response_format instance-attribute 

response_format: Literal[
    "json", "text", "srt", "verbose_json", "vtt"
]

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

temperature instance-attribute 

temperature: float

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.

timestamp_granularities instance-attribute 

timestamp_granularities: List[Literal['word', 'segment']]

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.