whatmodel.sh / tts / Maya1

Maya1

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

Maya1 is an open-weights text-to-speech model from Maya Research, released November 2025. Its published size is 3.3B parameters. Licence: apache-2.0.

37.7±6.2#90 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 Maya1, out of 148 with a score.

#modelscorewhereRAMreleased
113Magpie TTS Multilingual 357M NVIDIA39±6local~0.7GB2026-07
114Zonos v0.1 Zyphra39±4api price unknown +local~4.3GB2025-02
115Maya1 Maya Research38±6local~6.7GB2025-11
116Gemini 3.8 Flash TTS Google37±3api price unknown2026-09
117Pheme 300M PolyAI37±3local~3.6GB2024-01

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

$ what it's good at

other tests1 not in a task · 85% of its score
testresultvs the others in its rundifficultycountswhy
DailyDialog TTS · Whisper-large WER (UncovAI deepfake study)11.2% ✎▄··········█ beats 0/2avg 4.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%small run

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~8.42 GB, NVIDIA only · from huggingface.co/maya-research (official)
    pip install vllm snac soundfile && wget https://huggingface.co/maya-research/maya1/resolve/main/vllm_streaming_inference.py && python vllm_streaming_inference.py

Official weights and documentation: huggingface.co/maya-research ↗

$ how the score was worked out · Audio Deepfake Detection in t… 85%

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
Audio Deepfake Detection in the Age of Advanced Text-to-Speech models (arXiv:2601.20510v1)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%CC BY 4.0
prior · pull toward the middle▇▇▇▇▇ 15%
weighted average= 37.7

$ 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