Skip to main content
POST
/
v1
/
audio
/
speech
curl https://qingbo.dev/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "voice": "nova",
    "input": "欢迎使用 WaveAPI 文字转语音服务。"
  }' \
  --output output.mp3
Synchronous endpoint — returns an audio stream directly upon completion. 
curl https://qingbo.dev/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "voice": "nova",
    "input": "欢迎使用 WaveAPI 文字转语音服务。"
  }' \
  --output output.mp3

​
Available Models

Model IDDescription
tts-1Standard quality, low latency
tts-1-hdHigh-definition quality

​
Request Parameters

​
model
string
required
Model ID: tts-1, tts-1-hd
​
input
string
required
Text content to convert
​
voice
string
default:"alloy"
Voice type: alloy, echo, fable, onyx, nova, shimmer

​
Response

Returns an audio file stream (MP3 format). Save directly as a file.