whatmodel.sh / tts / Chatterbox Multilingual V3

Chatterbox Multilingual V3

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

Chatterbox Multilingual V3 is an open-weights text-to-speech model from Resemble AI, released April 2026. Its published size is 0.5B parameters. Licence: mit.

Catalogue identity notes

ResembleAI/chatterbox t3_mtl23ls_v3 + s3gen_v3 (Chatterbox Multilingual V3, 0.5B, 23 languages; files committed 2026-04/06). Distinct from the original English Chatterbox (id chatterbox) and Multilingual V2.

53.7±9.7#56 of 118 text-to-speech modelsfrom 1 benchmark result 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 Chatterbox Multilingual V3, out of 148 with a score, then more from Resemble AI.

#modelscorewhereRAMreleased
67Fasih-TTS-V1 NightPrince (Yahya Elnawasany)55±10local~1.9GB2026-07
68CosyVoice-300M Alibaba (FunAudioLLM)54±3local~2.3GB2024-07
69Chatterbox Multilingual V3 Resemble AI54±10local~3.2GB2026-04
70VibeVoice 1.5B Microsoft53±6local~5.4GB2025-08
71Lightning v3.1 Smallest.ai53±3api $17.50/M chars2026-03
more from Resemble AI
86Chatterbox Resemble AI50±5api $25.00/M chars +local~2.9GB2025-05

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

$ what it's good at

other tests1 not in a task · 62% of its score
testresultvs the others in its rundifficultycountswhy
Arabic TTS Arena · community blind A/B rating, 2026-09-24 snapshot1043.3 ✎▂▂··▃·█▅···▂ beats 4/12avg 1018▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%blunt

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~3.2 GB, NVIDIA only · from github.com/resemble-ai (official)
    git clone https://github.com/resemble-ai/chatterbox.git && cd chatterbox && pip install -e . && python -c "import torchaudio as ta; from chatterbox.mtl_tts import ChatterboxMultilingualTTS; m = ChatterboxMultilingualTTS.from_pretrained(device='cuda', t3_model='v3'); ta.save('out.wav', m.generate('Bonjour, comment ça va?', language_id='fr'), m.sr)"

Official weights and documentation: huggingface.co/ResembleAI ↗

$ how the score was worked out · Arabic TTS Arena (Navid AI) ·… 62%

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
Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-241▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇ 38%
weighted average= 53.7

$ 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