Benchmark Almanac

Turing TTS

Gemini 3.8 Flash TTS 10.5% leads since September 2026
Not in model cards

Listeners hear a human recording and a synthesized recording. The score measures how often listeners identify the synthesized recording as human.

The board reports the fool rate separately from naturalness.

Made by
Voice Arena
Kind
Speech recognition and translation
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Measures
Capability
In and out
Text → Audio
Interaction
Single turn
Items from
Live play or votes
Refresh
Live
Run by
A host
Last model added
September 2026
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 4 models we track

Gemini 3.8 Flash TTS leads with 10.5% among models released by September 2026 Gemini 3.8 Flash TTS leads with 10.5% among models released by September 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 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. This view shows only models we track, each at its best.

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:

  1. 1 Gemini 3.8 Flash TTS 10.5%
  2. 2 Gemini 3.8 Flash-Lite TTS 9.00%
  3. 3 Sonic-3.6 7.50%
  4. 4 Eleven v4 6.00%
  5. 5 Eleven v4 Turbo 6.00%
  6. 6 Simba 3.2 5.50%
  7. 7 Realtime TTS 2 5.00%
  8. 8 Gemini 3.1 Flash TTS 5.00%
  9. 9 Gradium-TTS 3.50%
  10. 10 Fish Audio Drama 3 3.00%

Source: Official Turing TTS leaderboard

#EntryScore ±SettingDateSource
1 Gemini 3.8 Flash TTS 10.5% 6.1 to 15.4 Sep 2026 Official leaderboard
2 Gemini 3.8 Flash-Lite TTS 9.00% 4.9 to 13.8 Sep 2026 Official leaderboard
3 Sonic-3.6 7.50% 4 to 11.4 Official leaderboard
4 Eleven v4 6.00% 2.5 to 10 Official leaderboard
5 Eleven v4 Turbo 6.00% 2.6 to 10.1 Official leaderboard
6 Simba 3.2 5.50% 2.5 to 9 Official leaderboard
7 Realtime TTS 2 5.00% 1.9 to 8.8 Official leaderboard
8 Gemini 3.1 Flash TTS 5.00% 2.1 to 8.4 Apr 2026 Official leaderboard
9 Gradium-TTS 3.50% 0.6 to 7.4 Official leaderboard
10 Fish Audio Drama 3 3.00% 0.6 to 6.1 Official leaderboard
#ModelScore ±SettingDateSource
1 Gemini 3.8 Flash TTS 10.5% 6.1 to 15.4 Sep 2026 Official leaderboard
2 Gemini 3.8 Flash-Lite TTS 9.00% 4.9 to 13.8 Sep 2026 Official leaderboard
3 Gemini 3.1 Flash TTS 5.00% 2.1 to 8.4 Apr 2026 Official leaderboard
4 Fish Audio Drama 3 3.00% 0.6 to 6.1 Official leaderboard

Rankings by part

We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Short, Medium and Long. Gemini 3.8 Flash TTS leads 3 of them, and Gemini 3.8 Flash-Lite TTS leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Short

4 models we track have a score here.

  1. 1 Gemini 3.8 Flash TTS 10.7%
  2. 2 Gemini 3.8 Flash-Lite TTS 7.14%
  3. 3 Fish Audio Drama 3 ↑1 3.57%
  4. 4 Gemini 3.1 Flash TTS ↓1 3.57%

2 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind
Own leaderboard Not tested since Sep 2026

Source: Official Turing TTS leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Gemini 3.8 Flash TTS Gemini 3.1 Flash TTS 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Gemini 3.8 Flash TTS

Source: Official Turing TTS leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 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%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 4 models we track, plus 6 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash-Lite TTS.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 10.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on voicearena.com: 4 rows for models we track and 6 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check