Skip to main content

GoogleCartesiaAudio matchupSpeech output

Gemini 3.1 Flash TTSvs.Sonic 3.6

Which model is better?

Sonic 3.6 does better in independent tests.

Independent tests
Gemini 3.1 Flash TTS0 of 3
Sonic 3.6ahead1 of 3
VoiceArena, Artificial Analysis, DesignArena
Popularity
Gemini 3.1 Flash TTS44
Sonic 3.639
out of 100
Weights and access
Gemini 3.1 Flash TTSproprietary
Sonic 3.6proprietary
Released
Gemini 3.1 Flash TTSn/a
Sonic 3.6n/a

Pick Gemini 3.1 Flash TTS for

No clear edge

Pick Sonic 3.6 for

Artificial Analysisleaning DesignArena

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

level

Gemini 3.1 Flash TTS is clearly ahead in 0 of 4 subtests, Sonic 3.6 in none. 4 are level.

VoiceArena TTS Elo: Hindi

Gemini 3.1 Flash TTS1,078
Sonic 3.61,094

95 % ranges 1,070 to 1,086 and 1,081 to 1,107, as of October 28, 2026

VoiceArena TTS Elo: Brazilian Portuguese

Gemini 3.1 Flash TTS1,089
Sonic 3.61,078

95 % ranges 1,081 to 1,097 and 1,062 to 1,094, as of October 28, 2026

VoiceArena TTS Elo: US English

Gemini 3.1 Flash TTS1,054
Sonic 3.61,059

95 % ranges 1,048 to 1,060 and 1,047 to 1,071, as of October 28, 2026

Show all 4 subtests
SubtestGemini 3.1 Flash TTSSonic 3.6Verdict
VoiceArena TTS Elo: Hindi1,0781,094level
VoiceArena TTS Elo: Brazilian Portuguese1,0891,078level
VoiceArena TTS Elo: US English1,0541,059level
VoiceArena TTS Elo: Mexican Spanish1,0861,081level

Source · latest October 28, 2026

Artificial Analysis

Sonic 3.6 ahead

Artificial Analysis Provider Voice Arena preference

Gemini 3.1 Flash TTS1,213
Sonic 3.61,293

95 % ranges 1,202 to 1,224 and 1,280 to 1,306, as of November 3, 2026

Source · latest November 3, 2026

DesignArena

Sonic 3.6 slightly ahead

DesignArena Audio Realism Elo

Gemini 3.1 Flash TTS1,025
Sonic 3.61,341

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.

Gemini 3.1 Flash TTSSonic 3.6
TaskSpeech outputSpeech output
DeveloperGoogleCartesia
StatusPreviewActive
Weightsproprietaryproprietary
Runs locallynono
Popularity (out of 100)4439