{
"text": "Hello."
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}API reference
Translate audio
Request format, responses, and capability boundaries.
{
"text": "Hello."
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"param": "<string>",
"code": "<unknown>"
}
}POST /v1/audio/translations
Send multipart with a translation-capable model and file. OpenAI-compatible semantics translate recordings into English; language does not select an arbitrary target language.
Read the JSON text field by default. Subtitle and verbose formats require model support. A transcription model is not automatically a translation model.
Integration guide and runnable example
简体中文Authorizations
模型调用 API Key,不是控制台登录凭据 / Model API key, not console login credentials
Body
multipart/form-data
当前密钥可用且支持此接口的模型 ID / Model ID available to the key and supporting this endpoint
Example:
"YOUR_MODEL_ID"
上传音频文件,保留正确扩展名;不是路径字符串或 URL / Uploaded audio file with correct extension, not a path string or URL
示例使用 json;text、srt、vtt、verbose_json 等需模型支持 / Examples use json; text, srt, vtt, verbose_json and other formats require model support
可选上下文提示,不是翻译目标语言 / Optional context hint, not the target translation language
采样温度,需模型支持 / Sampling temperature when supported
Response
由 response_format 决定;示例为 json / Determined by response_format; example uses json
- Option 1
- Option 2
转写或翻译文本,静音可能为空 / Transcribed or translated text; silence may yield empty text