UnderSky Docs

Text to Speech API

Complete reference for OpenAI-compatible speech synthesis through Tuzi API, including supported models, voices, formats, speed controls, authentication, pricing, and binary audio responses.

POST https://api.undersky.ai/v1/audio/speech

支持模型:tts-1、tts-1-hd、tts-1-1106、tts-1-hd-1106。

curl https://api.undersky.ai/v1/audio/speech \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","input":"Hello","voice":"alloy","response_format":"mp3"}' \
  --output speech.mp3

Pricing is based on input characters: tts-1 costs $12 per 1M characters, tts-1-hd costs $24, tts-1-1106 costs $300, and tts-1-hd-1106 costs $600.