POST
/
audio
/
transcriptions

Authorizations

Authorization
string
headerrequired

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

model
enum<string>
required

The name of the audio model to use.

Available options:
FunAudioLLM/SenseVoiceSmall

Response

200 - application/json

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

text
string
required

The transcribed text.

创建文本转语音请求参考音频列表获取