Humanness Index™ · TTS model
by Cartesia
Sonic 2 was Cartesia's second generation voice model, announced in early 2025 alongside the company's $64M Series A.
Standings as of Jul 28, 2026, 03:33 UTC
A real arena clip: a cloned source voice reading a customer support prompt at phone quality.
Sonic 2 was Cartesia's second generation voice model, announced in early 2025 alongside the company's $64M Series A. It cut time to first audio to roughly 90 ms, added a Turbo variant that reached 40 ms, and supported 15 languages. It established Sonic as one of the fastest production text to speech APIs before Sonic 3 took over as the flagship.
Sources: cartesia.ai
The fastest production TTS of its moment, with a 40 ms Turbo variant. In our 50 trial streaming benchmark Sonic 2 returned first audio in a median of 159 ms including network time.
Sources: docs.cartesia.ai
Standings as of Jul 28, 2026, 03:33 UTC
| Rank | Provider | Model | Humanness | Latency |
|---|---|---|---|---|
| #13 | MiniMax | Speech 2 Turbo | 70 | 315 ms |
| #14 | ElevenLabs | Flash v2.5 | 68 | 197 ms |
| #15 | Cartesia | Sonic 2 | 67 | 159 ms |
| #16 | Cartesia | Sonic 3 | 65 | 166 ms |
| #17 | Smallest.ai | Lightning v3.1 | 45 | 420 ms |
Compare the models in blind tests, read the methodology, or get in touch.
Build a TTS model? Add yours to the Index.
