Quickstart

Synthesize speech with one request.

1. Set your credentials

Get access to receive an API key, then export it together with your base URL:

export SONIX_URL="https://your-endpoint"
export SONIX_API_KEY="xy_live_..."

2. Make a request

curl "$SONIX_URL/v1/audio/speech" \
  -H "Authorization: Bearer $SONIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kokoro-82m",
    "input": "Hello from sonix.",
    "voice": "af_heart",
    "response_format": "wav"
  }' --output hello.wav

3. Play it

afplay hello.wav   # macOS
aplay hello.wav    # Linux

That's the whole integration. If your code already talks to ElevenLabs, keep it: the ElevenLabs-compatible surface accepts the same requests with your sonix key.