whatmodel.sh / tts / Parler-TTS Mini v1

Parler-TTS Mini v1

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

Parler-TTS Mini v1 is an open-weights text-to-speech model from Hugging Face (Parler-TTS), released August 2024. Its published size is 0.88B parameters. Licence: apache-2.0.

Catalogue identity notes

parler-tts/parler-tts-mini-v1 (description-prompted TTS; 877,842,290 parameters per HF safetensors metadata). Distinct from Parler-TTS Mini v0.1, Mini v1.1 and Large v1.

43.9±6.1#82 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 Parler-TTS Mini v1, out of 148 with a score, then more from Hugging Face (Parler-TTS).

#modelscorewhereRAMreleased
102GPT-SoVITS v2 RVC-Boss44±4local~1.1GB2024-08
103MeloTTS English MyShell44±5local~0.7GB2024-02
104Parler-TTS Mini v1 Hugging Face (Parler-TTS)44±6local~3.5GB2024-08
105Sonic (1) Cartesia42±3comparison only2024-05
106Nabra-82M v0.1 oddadmix42±10local~0.3GB2026-07
more from Hugging Face (Parler-TTS)
87Parler-TTS Mini v0.1 Hugging Face (Parler-TTS)49±14local~2.6GB2024-04
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 tests2 not in a task · 85% of its score
testresultvs the others in its rundifficultycountswhy
VERSA TTS demo · LibriSpeech test-clean UTMOS3.83 / 5 ✎▄·····▄·▄█·▄ beats 4/5easy · avg 4.11 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%at its level
VERSA TTS demo · LibriSpeech test-clean Whisper WER4.7% ✎▄··········█ beats 3/5avg 6.4%▇ 2.6%blunt · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~3.51 GB · from huggingface.co/parler-tts
    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-v1').to(d); t = AutoTokenizer.from_pretrained('parler-tts/parler-tts-mini-v1'); desc = 'A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker voice sounding clear and very close up.'; g = m.generate(input_ids=t(desc, return_tensors='pt').input_ids.to(d), prompt_input_ids=t('Hey, how are you doing today?', return_tensors='pt').input_ids.to(d)); sf.write('parler_tts_out.wav', g.cpu().numpy().squeeze(), m.config.sampling_rate)"

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

$ how the score was worked out · VERSA toolkit paper: TTS demo… 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
VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%CC BY 4.0
prior · pull toward the middle▇▇▇▇ 15%
weighted average= 43.9

$ 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