Speech Arena LeaderboardArtificial Analysis
Compare TTS models using each provider's own native voices.
Range | Creator | Model | Elo | 95% CI | Samples | Arena Voices | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 1-2 | Step Audio EditX (Mar 2026) | 1,118 | -15/15 | 1,268 | Feb 2026 | N/A | ||
| 2 | 1-2 | Fish Audio S2 Pro | 1,110 | -15/15 | 1,341 | Mar 2026 | $15.0 /1M chars | ||
| 3 | 3 | Voxtral TTS | 1,077 | -15/15 | 1,436 | Mar 2026 | $16.0 /1M chars | ||
| 4 | 4-5 | Kokoro 82M v1.0 | 1,060 | -11/11 | 5,256 | Jan 2025 | $0.7 /1M chars | ||
| 5 | 4-6 | Maya1 | 1,053 | -13/13 | 2,979 | Jun 2025 | N/A | ||
| 6 | 4-6 | Magpie-Multilingual 357M (Feb 2026) | 1,048 | -15/15 | 1,336 | Feb 2026 | N/A | ||
| 7 | 7-10 | Chatterbox | 1,011 | -12/12 | 4,577 | May 2025 | $25.0 /1M chars | ||
| 8 | 7-10 | Fish Speech 1.5 | 1,010 | -12/12 | 4,947 | Dec 2024 | $15.0 /1M chars | ||
| 9 | 7-10 | Magpie-Multilingual 357M | 1,005 | -13/13 | 3,352 | Jan 2026 | N/A | ||
| 10 | 10 | Zonos-v0.1 | 1,000 | 0/0 | 4,875 | Feb 2025 | $20.0 /1M chars | ||
| 11 | 11-12 | OpenVoice v2 | 959 | -14/14 | 2,901 | β | Apr 2024 | $8.3 /1M chars | |
| 12 | 11-12 | VibeVoice 7B | 958 | -14/14 | 1,859 | Aug 2025 | N/A | ||
| 13 | 13 | XTTS v2 | 908 | -15/15 | 2,356 | β | Nov 2023 | $40.4 /1M chars | |
| 14 | 14 | StyleTTS 2 | 882 | -16/16 | 2,297 | β | Jun 2023 | $2.8 /1M chars | |
| 15 | 15 | MetaVoice v1 | 836 | -18/18 | 1,242 | β | Feb 2024 | N/A |
1 API Pricing reflects the cost to generate 1M characters on the model creator's API with the model's default settings