whatmodel.sh / tts / Simple-TTS

Simple-TTS

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

Simple-TTS is an open-weights text-to-speech model from ASAPP Research (Justin Lovelace et al.), released October 2023.

Catalogue identity notes

asappresearch/simple-tts official checkpoint (README "Model Checkpoint": ckpt.tar.gz, U-ViT latent diffusion trained 200k steps on MLS English; the only released checkpoint). Code dump 2023-10-31 (paper: Lovelace et al., ICLR 2024). The repository has no licence file, so no weight licence is recorded.

31.0±5.1comparison only: no current run option verifiedfrom 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 Simple-TTS, out of 148 with a score.

#modelscorewhereRAMreleased
127VALL-E X (Plachtaa open implementation) Plachtaa (community)31±4local~1.6GB2023-08
128OuteTTS 0.2 500M OuteAI31±6local~0.9GB2024-11
129Simple-TTS ASAPP Research (Justin Lovelace et al.)31±5comparison only2023-10
130StyleTTS 2 (LibriTTS) Yinghao Aaron Li et al. (Columbia University)30±2local~0.9GB2023-11
131XTTS v2 Coqui30±2local~1.9GB2023-11

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
LibriSpeech test-clean 4-10 s cross-sentence · HuBERT-large WER4.1% ✎█···█··█···█ beats 2/3avg 0.7%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 52%typical
LibriSpeech test-clean 4-10 s cross-sentence · SIM-o (WavLM-TDCNN)50.3% ✎█··········█ beats 3/3easy · avg 72%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%at its level

$ where to run it

No verified API or download recorded yet · add one

Official weights and documentation: github.com/asappresearch ↗

$ how the score was worked out · DiTTo-TTS: Diffusion Transfor… 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
DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%CC BY 4.0
prior · pull toward the middle▇▇▇ 11%
weighted average= 31.0

$ 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