Voice Arena Japanese
Gemini 3.8 Flash TTS 1,188 leads since September 2026 Gemini 3.8 Flash TTS 1,232 leads since September 2026 Models generate speech in Japanese. Listeners compare anonymous clips, and preference votes determine independent language Elo ratings.
Each language has an independent leaderboard. Topic filters stay within its vote pool.
- Made by
- Voice Arena
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Ranked by votes
- Answers
- Open-ended
- Tasks
- All public
- Last in a system card
- September 2026
- Last model added
- September 2026
- Scores refreshed
- November 12th, 2026
Gemini 3.8 Flash TTS leads with 1,188 among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
Gemini 3.8 Flash TTS leads with 1,232, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
- Gemini 4 Carbon
- GPT-6.1 Sol
- GPT-6.1 Terra
- and 16 more
Bars start at 700.
- 1 Gemini 3.8 Flash TTS 1,188
- 2 ElevenLabs Eleven v4 1,154
- 3 Gemini 3.8 Flash-Lite TTS 1,136
- 4 Gemini 3.1 Flash TTS 1,130
- 5 ElevenLabs Eleven v3 1,031
- 6 GPT-4o Mini TTS 959
- 7 Cartesia Sonic-3.5 952
- 8 Cartesia Sonic-3 847
- 9 Grok TTS 837
- 10
Dragon HD Omni 767
Source: Official Voice Arena Japanese leaderboard
Bars start at 700.
- 1 Gemini 3.8 Flash TTS 1,232
- 2 Gemini 3.8 Flash-Lite TTS 1,152
- 3 Gemini 3.1 Flash TTS 1,130
- 4 GPT-4o Mini TTS 959
- 5 Grok TTS 837
- 6 Dragon HD Omni 767
Sources: Labs’ model cards and official Voice Arena Japanese leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 3.8 Flash TTS | 1,188 | Sep 2026 | Official leaderboard | |
| 2 | ElevenLabs Eleven v4 | 1,154 | Official leaderboard | ||
| 3 | Gemini 3.8 Flash-Lite TTS | 1,136 | Sep 2026 | Official leaderboard | |
| 4 | Gemini 3.1 Flash TTS | 1,130 | Apr 2026 | Official leaderboard | |
| 5 | ElevenLabs Eleven v3 | 1,031 | Official leaderboard | ||
| 6 | GPT-4o Mini TTS | 959 | Mar 2025 | Official leaderboard | |
| 7 | Cartesia Sonic-3.5 | 952 | Official leaderboard | ||
| 8 | Cartesia Sonic-3 | 847 | Official leaderboard | ||
| 9 | Grok TTS | 837 | Apr 2026 | Official leaderboard | |
| 10 | Dragon HD Omni | 767 | Dec 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 3.8 Flash TTS | 1,232 | Sep 2026 | Lab model card | |
| 2 | Gemini 3.8 Flash-Lite TTS | 1,152 | Sep 2026 | Lab model card | |
| 3 | Gemini 3.1 Flash TTS | 1,130 | Apr 2026 | Official leaderboard | |
| 4 | GPT-4o Mini TTS | 959 | Mar 2025 | Official leaderboard | |
| 5 | Grok TTS | 837 | Apr 2026 | Official leaderboard | |
| 6 | Dragon HD Omni | 767 | Dec 2025 | Official leaderboard |
Labs report scores for 2 models in their cards. Switch the scores above to rank them together.
3 models have held number one on the official leaderboard since 2023 3 models have held number one with claims included since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Voice Arena Japanese leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Voice Arena Japanese leaderboard and labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Sep 23, 2026 | Gemini 3.8 Flash TTS model card | 1232 | Voice Arena japanese, Elo, Gemini speech generation model page | Capabilities |
| Sep 23, 2026 | Gemini 3.8 Flash-Lite TTS model card | 1152 | Voice Arena japanese, Elo, Gemini speech generation model page | Capabilities |
2 lab claims next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| Gemini 3.8 Flash TTS | 1,232 Voice Arena japanese, Elo, Gemini speech generation model page | 1,188 Leaderboard | +44 |
| Gemini 3.8 Flash-Lite TTS | 1,152 Voice Arena japanese, Elo, Gemini speech generation model page | 1,136 Leaderboard | +16 |
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7% - LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%