API手册
创建语音转文本请求
创建音频转录。
AuthorizationBearer <token>required
添加 Header 'Authorization: Bearer {账户 API Key}' 进行鉴权
In: header
filefilerequired
要转录的音频文件对象（不是文件名）。 文件上传规格限制为：时长不超过 1 小时，文件大小不超过 50MB。
Format
binaryExample
"/path/to/file/audio.mp3"modelstringrequired
对应的模型名称。为更好地提升服务质量，我们会对本服务提供的模型进行定期变更，包括但不限于模型上下线和模型服务能力的调整。在可行的情况下，我们会通过公告或消息推送等适当方式通知您此类变更。
Value in
"FunAudioLLM/SenseVoiceSmall" | "TeleAI/TeleSpeechASR"Example
"FunAudioLLM/SenseVoiceSmall"Response Body
模型响应。响应头中包含 x-siliconcloud-trace-id 字段，作为请求的唯一追踪标识，便于日志查询和问题排查。
TypeScript Definitions
Use the response body type in TypeScript.
textstringrequired
音频转录后的文本内容。
curl --request POST \
--url https://api.siliconflow.cn/v1/audio/transcriptions \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-F "file=@path/to/your/audio.mp3" \
-F "model=FunAudioLLM/SenseVoiceSmall"
import requests
url = "https://api.siliconflow.cn/v1/audio/transcriptions"
file_path = "path/to/your/audio.mp3"
headers = {
"Authorization": "Bearer <YOUR_API_KEY>"
}
with open(file_path, "rb") as audio_file:
files = {
"file": ("audio.mp3", audio_file), # 根据文件类型调整 MIME 类型
"model": (None, "FunAudioLLM/SenseVoiceSmall")
}
response = requests.post(url, headers=headers, files=files)
fetch('https://api.siliconflow.cn/v1/audio/transcriptions', {
method: 'POST',
headers: {
'Authorization': 'Bearer <YOUR_API_KEY>'
},
body: JSON.stringify({
model: 'FunAudioLLM/SenseVoiceSmall',
file: 'path/to/your/audio.mp3'
})
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
{
"text": "string"
}{
"code": 20012,
"message": "string",
"data": "string"
}"Invalid token""Forbidden""404 page not found"{
"message": "Request was rejected due to rate limiting. If you want more, please contact contact@siliconflow.cn. Details:TPM limit reached.",
"data": "string"
}{
"code": 50505,
"message": "Model service overloaded. Please try again later.",
"data": "string"
}"string"