Subspace Institute

Aliyun API

Generates speech audio from the provided text using Aliyun TTS service

POST

Request Body

application/jsonOptional
textRequiredstring
Minimum length: 1Maximum length: 4096
voicestring

The voice to use for speech generation. Default is longxiaochun.

Default: "longxiaochun"
formatstring

The audio format to use for the output.

Default: "mp3"Value in: "mp3" | "wav" | "pcm"
sampleRateinteger

The sample rate for the audio output in Hz. Default is 22050.

Default: 22050
volumeinteger

The volume of the synthesized speech (0-100). Default is 50.

Default: 50Minimum: 0Maximum: 100
ratenumber

The speed of the synthesized speech (0.5-2). Default is 1.

Default: 1Minimum: 0.5Maximum: 2
pitchnumber

The pitch of the synthesized speech (0.5-2). Default is 1.

Default: 1Minimum: 0.5Maximum: 2
tokenRequiredstring

DashScope API key for authentication

Minimum length: 1
curl -X POST "https://tts-relay.laplace.cn/laplace/" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "床前明月光，疑是地上霜。举头望明月，低头思故乡。",
    "voice": "longxiaochun",
    "format": "mp3",
    "sampleRate": 22050,
    "volume": 50,
    "rate": 1,
    "pitch": 1,
    "token": "string"
  }'

Audio file containing the generated speech

null

OpenAI TTS API POST

Generates speech audio from the provided text using OpenAI's Text-to-Speech service

Azure AI Speech API POST

Generates speech audio from the provided text using Azure's Text-to-Speech service