Built in Python, StyleTTS2 is an open-source speech and audio tool maintained by yl4579. With 6.4k stars on GitHub, it was last updated in August 2024. Topics include adversarial-training, deep-learning and diffusion-models.
“StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models”
— yl4579, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 6,365 |
| Forks | 708 |
| Language | Python |
| License | MIT |
| Last updated | |
| Owner | yl4579 |
| Repository | yl4579/StyleTTS2 |
Tags
adversarial-trainingdeep-learningdiffusion-modelsganlatent-diffusionlatent-diffusion-modelspytorchspeaker-adaptation
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.