snakers4/silero-models
Silero Models: pre-trained text-to-speech models made embarrassingly simple
Offers end-to-end TTS across 100+ languages with SSML support, automated stress/homograph handling for Slavic languages, and multiple sampling rates (8kHz–48kHz). Deployed via PyTorch Hub or pip with on-demand model caching, supporting both CPU and GPU inference. Includes specialized variants for CIS languages with optional stress markup and Indic language support.
5,822 stars. Actively maintained with 8 commits in the last 30 days.
Stars
5,822
Forks
360
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 17, 2026
Commits (30d)
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/snakers4/silero-models"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
abus-aikorea/voice-pro
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot...
snakers4/silero-stress
Silero Stress — pre-trained enterprise-grade automated stress and homograph disambiguation for...
JSchmie/ScrAIbe-WebUI
WebUI for ScAIbe
isaiahbjork/orpheus-tts-local
Run Orpheus 3B Locally With LM Studio
aman179102/podvoice
Local-first CLI that turns Markdown scripts into multi-speaker podcast-style audio using Coqui XTTS v2.