Svara API

Svara is a multilingual text-to-speech API — natural, expressive speech across 50+ languages with low latency and an OpenAI-compatible surface.

• Drop-in compatible with the OpenAI audio/speech API — point your existing client at Svara and change the base URL + key.
• Hundreds of voices across languages and accents, plus voice cloning.
• Streaming audio for real-time playback.

Base URL

https://platform.kenpathlabs.com

All endpoints are served under /v1. Authenticate with a Svara API key (sk_live_…) — see Authentication.

Your first request

curl -X POST https://platform.kenpathlabs.com/v1/audio/speech \
  -H "Authorization: Bearer $SVARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "svara-tts-v1",
    "voice": "tara",
    "input": "Namaste! Welcome to Svara.",
    "response_format": "mp3"
  }' --output speech.mp3

Continue with the Quickstart.