Gemini 3.8 Flash TTS launch (Google DeepMind) Sep 23, 2026
Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS ranks first on 4 of the 7 benchmarks with five or more models scored.
14
Benchmarks with a score
4
Ranked first, out of five or more models
7
In the top three
Google DeepMind Sep 2026 Gemini 3.8 Flash TTS
Closed weights
No Epoch Capabilities Index score yet
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Voice Arena Hindi | 1,084 | #1 of 9 | Official leaderboard | |
| Voice Arena Arabic MSA | 1,192 | #1 of 7 | Official leaderboard | |
| Voice Arena Mexican Spanish | 1,138 | #1 of 7 | Official leaderboard | |
| Voice Arena Japanese | 1,188 | #1 of 6 | Official leaderboard | |
| Voice Arena Brazilian Portuguese | 1,097 | #2 of 7 | Official leaderboard | |
| Voice Arena US English | 1,063 | #2 of 7 | Official leaderboard | |
| Voice Arena Vietnamese | 1,122 | #2 of 7 | Official leaderboard | |
| Voice Arena Bahasa | 1,138 | #1 of 3 | Official leaderboard | |
| Voice Arena Tagalog | 1,130 | #1 of 3 | Official leaderboard | |
| Hume AI Overall Quality Index | 0.9 | #1 of 2 | Lab model card | |
| Voice Arena French | 1,084 | #1 of 2 | Official leaderboard | |
| Voice Arena German | 1,034 | #1 of 2 | Official leaderboard | |
| Voice Arena Indian English | 1,062 | #2 of 2 | Official leaderboard | |
| Hume AI Voice Design Benchmark | 71.4 | #1 of 1 | Lab model card |
Its lab's numbers next to 7 leaderboards
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
| Benchmark | Lab says | Board says | Gap |
|---|---|---|---|
| Voice Arena Japanese | 1,232 Voice Arena japanese, Elo, Gemini speech generation model page | 1,188 Leaderboard | +44 |
| Voice Arena Hindi | 1,106 Voice Arena hindi, Elo, Gemini speech generation model page | 1,084 Leaderboard | +22 |
| Voice Arena Mexican Spanish | 1,152 Voice Arena mexican spanish, Elo, Gemini speech generation model page | 1,138 Leaderboard | +14 |
| Voice Arena Vietnamese | 1,135 Voice Arena vietnamese, Elo, Gemini speech generation model page | 1,122 Leaderboard | +13 |
| Voice Arena Arabic MSA | 1,204 Voice Arena arabic msa, Elo, Gemini speech generation model page | 1,192 Leaderboard | +12 |
| Voice Arena Brazilian Portuguese | 1,104 Voice Arena brazilian portuguese, Elo, Gemini speech generation model page | 1,097 Leaderboard | +7 |
| Voice Arena US English | 1,061 Voice Arena us english, Elo, Gemini speech generation model page | 1,063 Leaderboard | −2 |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 7 of them aren't in the launch post.
Gemini 3.8 Flash TTS and Flash-Lite TTS, speech generation model page (Google DeepMind) Sep 23, 2026