Subspace Institute

StepFun API

Generates speech audio from the provided text using StepFun Text-to-Speech service

POST
/tts-stepfun
textstring
Length1 <= length <= 1024
voice?string | null

Desired voice. Either voice_id or timber_weights must be given as part of the parameters. Both system voice ids and cloned voice ids are supported

Default"cixingnansheng"
tokenstring

StepFun API key for authentication

Length1 <= length
volume?number

Volume of the speech

Range0.1 <= value <= 2
model?string

The model to be used for the speech

Default"step-tts-mini"

Response Body

curl -X POST "https://edge-workers.laplace.cn/laplace/tts-stepfun" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "感谢ドラゴンラプラスWeChat的SC:一发sc没被念到我就冷汗直流心跳加速头皮发麻双手痉挛两腿打颤,还不好意思刷弹幕说你漏了,我好怕你看到了装作没看到。我的sc通常很短只有一小时,只有短短的3600秒,但它存在的时候,我会用心跳来为它倒数。私のBANを解除してください。もう二度とスパムしません😭",
    "token": "string"
  }'
null
{
  "success": false,
  "message": "string",
  "code": "string",
  "type": "string"
}
{
  "success": false,
  "message": "string",
  "code": "string",
  "type": "string"
}