whatmodel.sh / tts / Parler-TTS Mini v0.1

Parler-TTS Mini v0.1

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

Parler-TTS Mini v0.1 is an open-weights text-to-speech model from Hugging Face (Parler-TTS), released April 2024. Its published size is 0.647B parameters. Licence: apache-2.0.

Catalogue identity notes

parler-tts/parler_tts_mini_v0.1 (647,027,186 parameters per HF safetensors metadata). Distinct from Parler-TTS Mini v1/v1.1.

48.9±14.4#69 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 Parler-TTS Mini v0.1, out of 148 with a score, then more from Hugging Face (Parler-TTS).

#modelscorewhereRAMreleased
85MMS TTS Amharic Meta50±16local~0.2GB2023-05
86Chatterbox Resemble AI50±5api $25.00/M chars +local~2.9GB2025-05
87Parler-TTS Mini v0.1 Hugging Face (Parler-TTS)49±14local~2.6GB2024-04
88Fish Speech 1.2 Fish Audio49±14local~1.2GB2024-07
89SILMA TTS v1 SILMA AI48±10local~2.7GB2026-03
more from Hugging Face (Parler-TTS)
104Parler-TTS Mini v1 Hugging Face (Parler-TTS)44±6local~3.5GB2024-08
133Parler-TTS Large v1 Hugging Face (Parler-TTS)29±3local~9.3GB2024-08

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

$ what it's good at

other tests1 not in a task · 17% of its score
testresultvs the others in its rundifficultycountswhy
TTSDS v1 · default four-factor score85.6% ✎▂▂····▃·▃▅▂█ beats 8/14very easy · avg 86%▇▇▇▇▇▇▇ 17%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~2.59 GB · from github.com/huggingface (official)
    pip install git+https://github.com/huggingface/parler-tts.git soundfile && python -c "import torch, soundfile as sf; from parler_tts import ParlerTTSForConditionalGeneration; from transformers import AutoTokenizer; d='cuda:0' if torch.cuda.is_available() else 'cpu'; m=ParlerTTSForConditionalGeneration.from_pretrained('parler-tts/parler_tts_mini_v0.1').to(d); t=AutoTokenizer.from_pretrained('parler-tts/parler_tts_mini_v0.1'); g=m.generate(input_ids=t('A female speaker delivers a slightly expressive speech with a very clear recording.', return_tensors='pt').input_ids.to(d), prompt_input_ids=t('Hello, world!', return_tensors='pt').input_ids.to(d)); sf.write('out.wav', g.cpu().numpy().squeeze(), m.config.sampling_rate)"

Weights and documentation: huggingface.co/parler-tts ↗

$ how the score was worked out · TTSDS v1 published results 17%

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
TTSDS v1 published results1▇▇▇▇▇ 17%MIT
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%
weighted average= 48.9

$ 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