Subspace Institute

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

Request Body

application/jsonOptional

textRequiredstring

Minimum length: 1Maximum length: 1024

referencesarray<object>

References to be used for the speech, this requires MessagePack serialization, this will override reference_voices and reference_texts

voicestring

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: "male-qn-qingse"

tokenRequiredstring

MiniMax API key for authentication

Minimum length: 1

groupIdRequiredstring

The group to which the user belongs. Use the pre-generated value. The value should be spliced at the end of the url that calls the API.

Minimum length: 1

modelstring

The model to be used for the speech

curl -X POST "https://tts-relay.laplace.cn/api/laplace/tts-minimax" \
  -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😭",
    "references": [
      {
        "audio": "string",
        "text": "string"
      }
    ],
    "voice": "male-qn-qingse",
    "token": "string",
    "groupId": "string",
    "model": "string"
  }'

Audio file containing the generated speech

null

MiniMax T2A API

Request Body

Response

TypeScript