snakers4/silero-models

Silero Models: pre-trained text-to-speech models made embarrassingly simple

60
/ 100
Established

This project offers pre-trained text-to-speech models that convert written text into natural-sounding spoken audio. You input text, select a voice and language, and receive an audio file of that text being spoken aloud. It's designed for anyone needing to generate speech from text, such as content creators, educators, or customer service departments.

5,822 stars. Actively maintained with 5 commits in the last 30 days.

Use this if you need to quickly and easily convert text into natural-sounding speech across multiple languages for various applications.

Not ideal if you require highly customized voice cloning or real-time, low-latency conversational AI without any development setup.

audio-content-creation e-learning voice-assistants multilingual-communication accessibility
No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

5,822

Forks

360

Language

Jupyter Notebook

License

Last pushed

Mar 17, 2026

Commits (30d)

5

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.