whatmodel.sh / tts / Kyutai TTS 1.6B en/fr

Kyutai TTS 1.6B en/fr

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Kyutai TTS 1.6B en/fr is an open-weights text-to-speech model from Kyutai, released July 2025. Its published size is 1.8B parameters. Licence: cc-by-4.0.

Catalogue identity notes

KyutAI-TTS as explicitly linked in the result row.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

Maker's explicit total for this checkpoint (backbone + depth transformer); excludes the Mimi codec. Name says 1.6B; the card corrects it to 1.8B.

47.0±5.2#74 of 118 text-to-speech modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.

$ how it compares

The text-to-speech models ranked either side of Kyutai TTS 1.6B en/fr, out of 148 with a score.

#modelscorewhereRAMreleased
91Vokan ShoukanLabs48±14comparison only2024-03
92Orpheus TTS 3B 0.1 (finetune-prod) Canopy Labs47±5api $15.00/M chars +local~2.4GB2025-03
93Kyutai TTS 1.6B en/fr Kyutai47±5local~4.1GB2025-07
94MiMo v2.5 TTS Xiaomi MiMo47±4comparison only2026-04
95Amphion VALL-E (LibriLight 6k) Amphion (CUHK-Shenzhen)47±14local~1.6GB2024-01

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 89% of its score
testresultvs the others in its rundifficultycountswhy
EmergentTTS · 6-category preference21.9% ✎▅▅▃▃█▅▅▃·▃·▅ beats 5/16hard · avg 30%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%at its level
EmergentTTS · 6-category WER12.7% ✎▂▄··▂▄▄··█▄▆ beats 11/16avg 16%▇▇▇▇▇▇▇▇ 20%blunt

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~4.07 GB, Mac only · from github.com/kyutai-labs
    git clone https://github.com/kyutai-labs/delayed-streams-modeling && cd delayed-streams-modeling && echo "Hey, how are you?" | uvx --with moshi-mlx python scripts/tts_mlx.py - audio_output.wav

Official weights and documentation: huggingface.co/kyutai ↗

$ how the score was worked out · EmergentTTS-Eval six-category… 89%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
EmergentTTS-Eval six-category leaderboard2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%Apache-2.0
prior · pull toward the middle▇▇▇ 11%
weighted average= 47.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json