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"
headers = {"Authorization": "Bearer YOUR_API_KEY"}
with open("path/to/your/audio.mp3", "rb") as audio_file:
files = {
"file": ("audio.mp3", audio_file),
"model": (None, "FunAudioLLM/SenseVoiceSmall")
}
response = requests.post(url, headers=headers, files=files)
print(response.text)
{
"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"