Cartesia

Ultra-low-latency TTS for realtime voice apps

cartesia.ai · Free tier; from ~$5/mo

Cartesia's Sonic models generate speech in tens of milliseconds — the TTS for voice agents where ElevenLabs feels slow.

Capabilities

Capabilities

  • ~40ms streaming TTS, voice cloning, on-device options; free tier then from ~$5/mo

Best for

  • Realtime voice-agent clones where response latency is the product

Not for

  • Long-form narration quality (ElevenLabs still leads on richness)