Pyyan / Compare / Voxtral Mini TTS 3 vs Fish Audio S2 Pro
Voxtral Mini TTS 3 vs Fish Audio S2 Pro
2 of 5Voice & Audio · verified 26 Oct 2026
Voxtral Mini TTS 3Mistralcurrent
Fish Audio S2 ProFish Audiocurrent| Specification | Voxtral Mini TTS 3 | Fish Audio S2 Pro |
|---|---|---|
| Summary | A frontier lab's first serious text to speech, priced well under the incumbents. | Top open-weights TTS. |
| Arena Elo | Not yet rated | 1123 |
| Price ($/M chars) | $13 | $15 |
| Clone from | ~30 min for Pro Voice | — |
| Open weights | Not stated | Yes |
| Category | Voice & Audio | Voice & Audio |
| Official | Mistral ↗ | Fish Audio ↗ |
Highlighted rows are where these differ.
Voxtral Mini TTS 3
- 35+ languages and 50+ dialects, in batch and realtime modes
- Pro Voice adapts to a speaker from about thirty minutes of audio
- Ships with a LiveKit voice agent SDK that completes a turn in under a second over SIP or WebRTC
- Mistral has not stated a licence, so whether the weights are open is not yet knowable
Best for multilingual synthesis inside a voice agent.
Fish Audio S2 Pro
- 80+ languages, 50+ emotion controls
- Roughly six times cheaper than ElevenLabs
Best for self-hosting.