Fish AudioMistral AIAudio matchupSpeech output
Fish Audio S2.1 Provs.Voxtral Mini TTS 3
Which model is better?
Voxtral Mini TTS 3 does better in independent tests.
Pick Fish Audio S2.1 Pro for
Pick Voxtral Mini TTS 3 for
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
Artificial Analysis
Voxtral Mini TTS 3 aheadVoxtral Mini TTS 3 is clearly ahead in 2 of 2 subtests, Fish Audio S2.1 Pro in none.
Artificial Analysis Controlled Voice Arena Elo
95 % ranges 996 to 1,022 and 1,054 to 1,084, as of November 3, 2026
Artificial Analysis Provider Voice Arena preference
95 % ranges 1,170 to 1,196 and 1,204 to 1,232, as of November 3, 2026
Source · latest November 3, 2026
DesignArena
Voxtral Mini TTS 3 slightly aheadDesignArena Audio Realism Elo
as of October 28, 2026
Source · latest October 28, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Fish Audio S2.1 Pro | Voxtral Mini TTS 3 | |
|---|---|---|
| Task | Speech output | Speech output |
| Developer | Fish Audio | Mistral AI |
| Status | Active | Public preview |
| Released | June 23, 2026 | October 20, 2026 |
| Weights | proprietary | n/a |
| Runs locally | no | no |
| Price | Free through 2026-11-30 under fair-use rules; changes with advance notice | USD 13 per 1 million characters; cached rate USD 1.30 per 1 million characters |
| Popularity (out of 100) | 0 | 0 |