curl --request POST \
--url https://api.powertokens.ai/v1/audio/speech \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "qwen3-tts-instruct-flash",
"input": "请用略快的语速介绍这款产品。",
"voice": "Cherry",
"instructions": "语速较快,带有上扬语调。",
"optimize_instructions": false,
"language_type": "Chinese"
}
'"<string>"调用阿里 qwen3-tts-instruct-flash 生成语音。
响应约定:
302 Found + Location;text/event-stream,透传阿里 SSE 数据。curl --request POST \
--url https://api.powertokens.ai/v1/audio/speech \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "qwen3-tts-instruct-flash",
"input": "请用略快的语速介绍这款产品。",
"voice": "Cherry",
"instructions": "语速较快,带有上扬语调。",
"optimize_instructions": false,
"language_type": "Chinese"
}
'"<string>"Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
流式调用成功,返回阿里 SSE 数据。项目内部结算会读取 usage.characters 作为统一输入音频字符数。
The response is of type string.