Skip to content
Local AI Wizard
Your machine
Theme

StyleTTS 2

StyleTTS

Weights license: Publisher terms: MIT (code); pre-trained models under StyleTTS 2 synthetic-speech disclosure terms · code and components may use other terms

QualityNo public, reusable benchmark result covers this model.No comparable score
Memory neededNot verifiedNo estimate without a verified parameter basis
ParametersNot reported, or a community distributionNot reported, or a community distribution
Published repository size0.8 GBAll published files · not runtime memory

Quality

No comparable score

No public, reusable benchmark result covers this model. Leaderboard (link only)

Reported by the publisher

This model card has not been read for benchmark results yet. card not read yet

Runs on

No memory requirement to match

Without a parameter count with a known basis or a documented memory path, no hardware is grouped. Nothing is guessed.

Measured speed

No published measurement for this checkpoint

Speed (real-time factor, or seconds per clip) is shown only when a source publishes it with hardware, build and setup. It is never estimated.

How to run

This catalog has not verified hardware requirements for this entry. Actual memory depends on precision, resolution, duration and offload; consult the official source.

Documented ways to run it

The model card points to another page without a command of its own

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
github.com/yl4579/StyleTTS2
Task
text-to-speech
Architecture
Technical details pending review
Weight license
Publisher terms: MIT (code); pre-trained models under StyleTTS 2 synthetic-speech disclosure terms
Commercial use
The pre-trained model terms only require disclosing synthetic speech; they neither grant nor refuse commercial use
Repository size
0.77 GB
Released
yl4579/StyleTTS2 commit history (GitHub), commit fe76a75 "Update README.md" adding "The pretrained StyleTTS 2 on LJSpeech corpus in 24 kHz can be downloaded" · read 2026-10-19source

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-22. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.