# TTS Arena V2

People listen to two computer-generated voices reading the same text and pick the one that sounds better. The ranking shows which text-to-speech systems people actually prefer.

Category: tts. Type: arena. Status: active.
Metric: Elo rating from blind human votes (higher = preferred more often) (higher is better).
Source: TTS-AGI community (Hugging Face) — https://tts-agi-tts-arena-v2.hf.space/api/leaderboard, results as of 2026-11-11, retrieved 2026-11-17, license: not stated.

| Rank | Model | Elo | Win rate (%) | Votes |
|---|---|---|---|---|
| 1 | Aurora | 1687 | 73.4 | 312 |
| 2 | star-june-2026 | 1633 | 64.7 | 295 |
| 3 | Inworld TTS MAX | 1567 | 63.8 | 1193 |
| 4 | CastleFlow v1.0 | 1558 | 61.9 | 1490 |
| 5 | Inworld TTS 1.5 MAX | 1565 | 59.7 | 390 |
| 6 | Hume Octave | 1551 | 59.7 | 949 |
| 7 | Inworld TTS | 1543 | 60.0 | 1712 |
| 8 | Papla P1 | 1552 | 61.2 | 836 |
| 9 | Gradium TTS 2026.10 | 1588 | 62.7 | 102 |
| 10 | Gradium TTS (pre-2026.08) | 1554 | 53.7 | 259 |
| 11 | MiniMax Speech 2.8 HD | 1545 | 54.2 | 253 |
| 12 | OpenAudio S2 | 1539 | 52.2 | 322 |
| 13 | Lightning v3.1 Pro | 1544 | 53.6 | 295 |
| 14 | Deepdub eTTS 3.2 | 1532 | 52.1 | 217 |
| 15 | Eleven Multilingual v2 | 1507 | 54.0 | 968 |
| 16 | Eleven Turbo v2.5 | 1505 | 53.5 | 951 |
| 17 | MiniMax Speech 2.6 Turbo | 1525 | 50 | 270 |
| 18 | Eleven Flash v2.5 | 1503 | 53.2 | 964 |
| 19 | MiniMax Speech 02 HD | 1503 | 53.7 | 1028 |
| 20 | Eleven v3 | 1521 | 49.3 | 288 |
| 21 | MiniMax Speech 2.6 HD | 1504 | 47.5 | 284 |
| 22 | MiniMax Speech 2.8 Turbo | 1502 | 48.2 | 282 |
| 23 | MiniMax Speech 02 Turbo | 1483 | 50.9 | 1037 |
| 24 | Parmesan | 1481 | 52.4 | 984 |
| 25 | Kokoro v1.0 | 1470 | 48.8 | 903 |

Notes: Rank/order as served by the site API; as_of is the Space's last modified date. Includes some preliminary/stealth entries.
