main
1# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
2
3from typing import Optional
4from typing_extensions import Literal
5
6from ..._models import BaseModel
7
8__all__ = ["AudioTranscription"]
9
10
11class AudioTranscription(BaseModel):
12 language: Optional[str] = None
13 """The language of the input audio.
14
15 Supplying the input language in
16 [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
17 format will improve accuracy and latency.
18 """
19
20 model: Optional[
21 Literal["whisper-1", "gpt-4o-mini-transcribe", "gpt-4o-transcribe", "gpt-4o-transcribe-diarize"]
22 ] = None
23 """The model to use for transcription.
24
25 Current options are `whisper-1`, `gpt-4o-mini-transcribe`, `gpt-4o-transcribe`,
26 and `gpt-4o-transcribe-diarize`. Use `gpt-4o-transcribe-diarize` when you need
27 diarization with speaker labels.
28 """
29
30 prompt: Optional[str] = None
31 """
32 An optional text to guide the model's style or continue a previous audio
33 segment. For `whisper-1`, the
34 [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting).
35 For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the
36 prompt is a free text string, for example "expect words related to technology".
37 """