Voxtral 3 Release - Pronunciation Control - Overall: leaderboard
Voxtral 3 release evaluation (2026-10-20): exact chart marks retain model, series and score. FLEURS 45 macro-averages WER, using CER for Japanese, Korean, Thai and Chinese; language forced/inferred runs stay separate. Diarization averages cpWER over AMI-IHM, AMI-SDM, Switchboard, CallHome and AISHELL-4 with 30-minute clips. Context-bias recall uses Earnings22. Realtime latency configurations remain distinct. TTS tests retain their release-specific populations and judge; chart x-axis prices are never scores. Accurate Pronunciation (%).
Metric: Accurate Pronunciation (%). Source: mistral.ai. Saturation forecast: Rough model projection: around 2026. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Voxtral Mini TTS 3.0 | 86.83 | |
| 2 | Inworld TTS-2 | 81.83 | |
| 3 | Cartesia Sonic 3.6 | 81.17 | |
| 4 | Inworld TTS-2 Flash | 80.17 | |
| 5 | Fish Drama 3 | 69 | |
| 6 | Qwen-Audio 3.1 Flash | 68.5 | |
| 7 | Eleven v4 Turbo | 68.33 | |
| 8 | Eleven v4 | 68.17 | |
| 9 | Deepgram Flux TTS | 65.33 | |
| 10 | Qwen-Audio 3.0 Plus | 44.17 |
Interactive version: theaggregate.ai/benchmark?slug=voxtral-3-release-pronunciation-control-overall · How It Works · Data refreshed daily, snapshot 2026-10-21.