{
  "slug": "cartesia",
  "name": "Cartesia",
  "url": "https://cartesia.ai",
  "cat": "gen",
  "group": "ai",
  "tagline": "Ultra-low-latency TTS for agents",
  "price": "Free 20K credits, personal use only. Pro $5/mo (100K), Startup $49 (1.25M), Scale $299 (8M). TTS is 1 credit/character, Ink STT 1 credit/second, Line voice agents $0.014/min.",
  "tier": "mixed",
  "pick": false,
  "what": "Voice infrastructure company built on state-space models. <b>Sonic 3</b> does text-to-speech in 40-plus languages with emotion controls, laughter tags and voice cloning from a 3-second sample. Ink handles speech-to-text and Line orchestrates phone-based voice agents.",
  "why": "Around 90ms time-to-first-audio, and 40ms on Sonic Turbo - fast enough that a phone agent never sounds like it is thinking. That latency, not raw voice beauty, is why realtime builders pick it over ElevenLabs.",
  "warn": "The free tier is <b>personal use only</b>; any commercial deployment needs at least the $5 Pro plan. Pro voice cloning bills at 1.5 credits per character rather than 1, so cloned-voice costs run 50% above the headline rate.",
  "install": "Low-latency streaming API with WebSocket support; SDKs for Python, Node and Rust.",
  "category": {
    "key": "gen",
    "name": "AI media generation",
    "desc": "Image, video, voice and music. Commercial rights differ wildly by tier — check every warn.",
    "group": "ai",
    "groupName": "Put AI inside it"
  },
  "freshness": null,
  "health": {
    "ok": true,
    "status_code": 200,
    "final_url": "https://www.cartesia.ai/",
    "checked_at": "2026-08-18T23:43:12.623+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}