Create speech-to-text request

POST

/siliconflow/v1/audio/transcriptions

Model supported: FunAudioLLM/SenseVoiceSmall
Free of charge

Request

Header Params

Authorization

string

optional

Example:

Bearer {{YOUR_API_KEY}}

Body Params multipart/form-data

file

required

model

string

required

Example:

FunAudioLLM/SenseVoiceSmall

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/siliconflow/v1/audio/transcriptions' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--form 'file=@""' \
--form 'model="FunAudioLLM/SenseVoiceSmall"'

Responses

🟢200成功

application/json

Body

text

string

required

Example

{"text":"I am so happy spring festival is coming.😊"}

Modified at 2025-06-16 05:40:28

Delete reference audio

Create text-to-speech request