Speech Synthesis API (POST /v1/audio/speech)

Generates audio from text matching the OpenAI /v1/audio/speech specification.

---

📥 Request Body

Field	Type	Required	Default	Description
model	string	Optional	edgetts	Model or Provider ID (tts-1, edgetts, kokoro)
input	string	Yes	-	Text to synthesize (up to 8,192 characters)
voice	string	Optional	alloy	Voice ID or alias (alloy, zh-CN-XiaoxiaoNeural)
response_format	string	Optional	mp3	Format: mp3, opus, aac, flac, wav, pcm
speed	float	Optional	1.0	Speed rate multiplier (0.25 to 4.0)
stream	boolean	Optional	false	Enable HTTP Chunked audio streaming

---

💡 Example

curl http://localhost:8030/v1/audio/speech \
  -H "Authorization: Bearer sk-onetts-v1-k9L3mX8QZ2sT4vA7wE1rY6u" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "OneTTS delivers ultra-fast speech synthesis.",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output speech.mp3