#5555th of 67 in VoiceFor voice, speech and music
silero-models
Pretrained PyTorch text-to-speech models for Russian, CIS and Indic languages
- Stars
- 6.2k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- Jupyter Notebook
5,815 on 3 Apr 20266,155 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Silero Models provides pretrained TTS models loaded through torch.hub or the `silero` pip package, with models downloaded on demand. V5 models support SSML and 8000, 24000 and 48000 Hz sampling rates. Russian models add automatic stress and homograph handling, and separate models cover Turkic, Caucasian, other CIS and Indic languages.
Who it is for: Developers needing offline TTS for Russian and CIS languages in Python
Strengths
- Covers many minority CIS languages (Turkic, Caucasian) rarely supported elsewhere
- Russian models include automatic stress, homographs and question intonation
- Loads in a few lines via pip or torch.hub; models fetched on demand
- V5 models support SSML and three sampling rates (8k, 24k, 48k)
Weaknesses
- Main license is CC BY-NC 4.0, non-commercial; only the CIS base models are MIT
- Only TTS is described in the visible README; no speech-to-text covered
- No Docker image or HTTP server provided; you wrap the Python API yourself
- V5 CIS base models need manually placed stress marks, or use the nostress variant
What it needs
- GPU optional
- Needs PyTorch
- Models: PyTorch TTS models, SSML
Quick answers
Is silero-models open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Does silero-models need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |