Voice API by Pyonair

Give your product a voice.

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.

Three ways to use Sona

Everything runs through one secure endpoint with your private API key.

🗣️

Text to speech

Send text, get natural-sounding speech back as an MP3. 16 voices, adjustable speed, multiple languages.

POST /v1/tts
💬

Multi-speaker conversation

Provide a script with two or more speakers and Sona stitches it into one audio file, great for podcasts and walkthroughs.

POST /v1/tts/conversation
🎙️

Voice cloning

Upload a short reference clip and Sona speaks new text in that voice. Perfect for a branded or personal voice.

POST /v1/clone

16 built-in voices

Pick a voice by name in any request. New voices added over time.

Female
heartsky sarahnova jessicaisabella
Male
ericecho fenrirliam onyxpuck
British
georgeemma

Quick start

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

Endpoints

Method & pathWhat it does
POST /v1/ttsText → speech (MP3)
POST /v1/tts/conversationMulti-speaker script → one MP3
POST /v1/cloneReference clip + text → cloned speech
GET /v1/voicesList available voices
GET /healthService status
Authentication. Every request needs your private API key, sent as a header: 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.