GoogleFish AudioAudio matchupSpeech output
Gemini 3.1 Flash TTSvs.Fish Audio S2 Pro
Which model is better?
Gemini 3.1 Flash TTS does better in independent tests, while Fish Audio S2 Pro is available with open weights.
Pick Gemini 3.1 Flash TTS for
Pick Fish Audio S2 Pro 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”.
VoiceArena
Gemini 3.1 Flash TTS aheadGemini 3.1 Flash TTS is clearly ahead in 1 of 2 subtests and slightly in 1, Fish Audio S2 Pro in none.
VoiceArena TTS Elo: US English
95 % ranges 1,048 to 1,060 and 929 to 943, as of October 28, 2026
VoiceArena TTS v1, US English, All, Elo
as of October 17, 2026
Source · latest October 28, 2026
Artificial Analysis
Gemini 3.1 Flash TTS aheadArtificial Analysis Provider Voice Arena preference
95 % ranges 1,202 to 1,224 and 1,097 to 1,119, as of November 3, 2026
Source · latest November 3, 2026
Hume AI
Gemini 3.1 Flash TTS slightly aheadHume Real World VoiceEQ expressivity-reliability frontier score
as of October 17, 2026
Source · latest October 17, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Gemini 3.1 Flash TTS | Fish Audio S2 Pro | |
|---|---|---|
| Task | Speech output | Speech output |
| Developer | Fish Audio | |
| Status | Preview | Open weights |
| Released | n/a | March 9, 2026 |
| Weights | proprietary | open |
| Runs locally | no | yes |
| Popularity (out of 100) | 44 | 51 |