whatmodel.sh / tts / Piper (en_US lessac medium)

Piper (en_US lessac medium)

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

Piper (en_US lessac medium) is an open-weights text-to-speech model from Open Home Foundation (Piper), released June 2023. Licence: mit.

Catalogue identity notes

Piper voice en_US-lessac-medium from rhasspy/piper-voices (en/en_US/lessac/medium/en_US-lessac-medium.onnx, 63,201,294 bytes), run with the maintained piper-tts runtime (OHF-Voice/piper1-gpl, GPL-3.0). Voice files are MIT on Hugging Face; the lessac training data carries the Blizzard 2013 research licence. Other Piper voices are separate checkpoints.

46.6±5.0#76 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 Piper (en_US lessac medium), out of 148 with a score, then more from Open Home Foundation (Piper).

#modelscorewhereRAMreleased
94MiMo v2.5 TTS Xiaomi MiMo47±4comparison only2026-04
95Amphion VALL-E (LibriLight 6k) Amphion (CUHK-Shenzhen)47±14local~1.6GB2024-01
96Piper (en_US lessac medium) Open Home Foundation (Piper)47±5local~0.1GB2023-06
97Vevo (Amphion) Amphion (CUHK-Shenzhen)46±3local~6.8GB2024-12
98Qwen3-TTS 12Hz 0.6B CustomVoice Alibaba (Qwen)46±6comparison only2026-01
more from Open Home Foundation (Piper)
137Piper (tr_TR dfki medium) Open Home Foundation (Piper)26±4local~0.1GB2023-06

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

$ what it's good at

other tests2 not in a task · 90% of its score
testresultvs the others in its rundifficultycountswhy
Paradee small-TTS comparison · 200 WikiText-103 sentences · UTMOS (utmos22_strong)4.36 / 5 ✎█······█···█ beats 1/2easy · avg 4.39 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%small run
Paradee small-TTS comparison · 200 WikiText-103 sentences · Whisper-base WER8.8% ✎▄··········█ beats 0/2avg 5.6%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%small run

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.06 GB · from github.com/OHF-Voice (official)
    pip install piper-tts && python3 -m piper.download_voices en_US-lessac-medium && python3 -m piper -m en_US-lessac-medium -f test.wav -- 'This is a test.'

Weights and documentation: huggingface.co/rhasspy ↗

$ how the score was worked out · Paradee: Distilling Kokoro-82… 90%

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
Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparison2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%CC BY 4.0
prior · pull toward the middle▇▇▇ 10%
weighted average= 46.6

$ 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