Benchmark Almanac

Voice Arena French

Gemini 3.8 Flash TTS 1,084
Not in model cards

Models generate speech in French. 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 model added
September 2026
Scores refreshed
November 12th, 2026
7
Entries on its own leaderboard, 2 models we track

Gemini 3.8 Flash TTS leads with 1,084

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.

Bars start at 900.

  1. 1,084 Gemini 3.8 Flash TTS
  2. 1,057 Gemini 3.8 Flash-Lite TTS
  3. 1,056 ElevenLabs Eleven v4 Turbo
  4. 1,022 Cartesia Sonic-3.6
  5. 946 Gradium-TTS
  6. 924 Inworld Realtime TTS 2
  7. 911 Fish Audio Drama 3

Bars start at 900.

  1. 1 Gemini 3.8 Flash TTS 1,084
  2. 2 Gemini 3.8 Flash-Lite TTS 1,057
  3. 3 ElevenLabs Eleven v4 Turbo 1,056
  4. 4 Cartesia Sonic-3.6 1,022
  5. 5 Gradium-TTS 946
  6. 6 Inworld Realtime TTS 2 924
  7. 7 Fish Audio Drama 3 911

Source: Official Voice Arena French leaderboard

#EntryScoreSettingDateSource
1 Gemini 3.8 Flash TTS 1,084 Sep 2026 Official leaderboard
2 Gemini 3.8 Flash-Lite TTS 1,057 Sep 2026 Official leaderboard
3 ElevenLabs Eleven v4 Turbo 1,056 Official leaderboard
4 Cartesia Sonic-3.6 1,022 Official leaderboard
5 Gradium-TTS 946 Official leaderboard
6 Inworld Realtime TTS 2 924 Official leaderboard
7 Fish Audio Drama 3 911 Official leaderboard

Scores over time

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

On the benchmark’s own leaderboard
1,050 1,060 1,070 1,080 1,090 1,050 1,060 1,070 1,080 1,090

Source: Official Voice Arena French leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Audio and video

All 232 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%