whatmodel.sh / tts / Wayu-Paxa-TTS-Edge

Wayu-Paxa-TTS-Edge

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

Wayu-Paxa-TTS-Edge is an open-weights text-to-speech model from Wayu Research / Paxa Labs, released August 2026. Its published size is 0.082B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

wayu-ai/wayu-paxa-tts-edge, fixed-voice Thai TTS described in arXiv:2609.03502v1.

Model information sources

· Parameter count ↗

Official wayu-ai model card for this exact checkpoint; card table also lists "Wayu-Paxa-TTS-Edge | 82M". Whole released model as stated by the maker.

63.8±3.9#22 of 118 text-to-speech modelsfrom 3 benchmark results across 1 source

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 Wayu-Paxa-TTS-Edge, out of 148 with a score.

#modelscorewhereRAMreleased
27VoxCPM2 OpenBMB64±1local~2.3GB2026-04
28Fun-CosyVoice3-0.5B-2512 Alibaba (FunAudioLLM)64±1local~5.4GB2025-12
29Wayu-Paxa-TTS-Edge Wayu Research / Paxa Labs64±4local~0.3GB2026-08
30Eleven Turbo v2.5 ElevenLabs64±4api $50.00/M chars2024-07
31Fish Audio S2.1 Pro Fish Audio63±3api $15.00/M chars2026-06

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

$ what it's good at

other tests3 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
Wayu Thai TTS eval · 1,531-item Challenge-Set keyword accuracy lab68.2% ✎█···█······█ beats 0/2medium · avg 48%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%at its level · small run
Wayu Thai TTS eval · English CER on 500 held-out LibriTTS lines (Whisper Large V3) lab1.1% ✎█······█···█ beats 0/2avg 3.6%▇▇▇▇▇▇▇▇▇▇▇▇ 31%small run
Wayu Thai TTS eval · 500-utterance Thai CER (Typhoon Whisper Large V3) lab3.7% ✎█······█···█ beats 1/2avg 12%▇▇▇▇▇▇▇▇▇▇▇ 29%small run

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.33 GB · from huggingface.co/wayu-ai (official)
    pip install git+https://github.com/wayu-research/wayu-tts-inference && wayu-tts "สวัสดีค่ะ" --voice f_young_clear --out hello.wav

Official weights and documentation: huggingface.co/wayu-ai ↗

$ how the score was worked out · Building and Evaluating Fixed… 94%

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
Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1) · lab-reported3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%CC BY 4.0
prior · pull toward the middle▇▇ 6%
weighted average= 63.8

$ 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