Leaderboard
Human-preference Elo for text-to-speech models from the Artificial Analysis Arena — open-weight and proprietary voices, ranked head-to-head.
| # | Model | Elo |
|---|---|---|
| 1 | Falcon 2 Murf AI | 1,155 |
| 2 | Kokoro 82M v1.0 Kokoro | 1,060 |
| 3 | Maya1 Maya Research | 1,040 |
| 4 | Higgs Audio V3 TTS Boson AI | 1,037 |
| 5 | Chatterbox Resemble AI | 1,019 |
| 6 | Zonos-v0.1 Zyphra | 1,000 |
| 7 | VibeVoice 1.5B Microsoft | 962 |
| 8 | XTTS v2 Coqui | 915 |
Leaderboard data is cached from Artificial Analysis Arena and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.