API手册
创建语音转文本请求
Creates an audio transcription.
POST
/
audio
/
transcriptions
Authorizations
Authorization
string
headerrequiredBearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
multipart/form-data
file
file
requiredThe audio file object (not file name) to transcribe
model
enum<string>
requiredThe 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
requiredThe transcribed text.