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 | Kokoro 82M v1.0 Kokoro | 1,055 |
| 2 | Maya1 Maya Research | 1,041 |
| 3 | Higgs Audio V3 TTS Boson AI | 1,040 |
| 4 | Chatterbox Resemble AI | 1,012 |
| 5 | Zonos-v0.1 Zyphra | 1,000 |
| 6 | VibeVoice 1.5B Microsoft | 967 |
| 7 | VibeVoice 7B Microsoft | 954 |
| 8 | XTTS v2 Coqui | 914 |
| 9 | Falcon Murf AI | 862 |
Leaderboard data is cached from Artificial Analysis Arena and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.