Sona turns text into natural speech in 16 voices, holds multi-speaker conversations, and clones a voice from a short sample. One base URL, one key, audio back in seconds.
Everything runs through one secure endpoint with your private API key.
Send text, get natural-sounding speech back as an MP3. 16 voices, adjustable speed, multiple languages.
Provide a script with two or more speakers and Sona stitches it into one audio file, great for podcasts and walkthroughs.
Upload a short reference clip and Sona speaks new text in that voice. Perfect for a branded or personal voice.
Pick a voice by name in any request. New voices added over time.
Two lines to your first audio file. Replace the key with the one you were given.
# Text to speech → saves speech.mp3 curl -X POST https://sona.pyonair.com/v1/tts \ -H "X-API-Key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"text":"Hello from Sona.","voice":"heart","speed":1.0}' \ --output speech.mp3
| Method & path | What it does |
|---|---|
POST /v1/tts | Text → speech (MP3) |
POST /v1/tts/conversation | Multi-speaker script → one MP3 |
POST /v1/clone | Reference clip + text → cloned speech |
GET /v1/voices | List available voices |
GET /health | Service status |
X-API-Key: YOUR_API_KEY (or
Authorization: Bearer YOUR_API_KEY). Keep it secret.
Each customer gets their own key, so usage is tracked and managed separately.