# snakers4/silero-models

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

Repository: https://github.com/snakers4/silero-models
Canonical: https://ross.abutalabs.com/products/silero-models
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: speech-to-text, pretrained-models, pytorch, colab, torch-hub, text-to-speech, tts-models, speech, speech-synthesis, tts, kazakh, russian, ukrainian, uzbek, azerbaijani, belarus, tajik, kyrgyz, armenian, georgian
Last push: 2026-07-31T16:28:45+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 87, longevity 100
- inputs: {"age_days": 2182, "days_push": 33, "days_rel": 90, "gap_med": 23, "n_releases_24m": 6}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6082, forks 372 (observed 2026-08-28T04:09:34.876817+00:00)

## What it is
A collection of pre-trained, end-to-end text-to-speech models usable via PyTorch Hub or a pip package with one-line usage. It supports many languages including Russian, Ukrainian, Kazakh, and other Turkic, Caucasian, and Indic languages, with fast CPU and GPU inference.

## Use cases
- convert text to natural-sounding speech in python
- add russian text-to-speech with automated stress to my app
- generate speech audio for underrepresented languages like kazakh or uzbek
- run tts fast on cpu without a gpu
- use pretrained tts models via torch hub
- synthesize speech with ssml markup

## When to choose
- you need simple, one-line TTS in PyTorch for many languages
- you need fast CPU inference for speech synthesis
- you need voices for Russian, Turkic, Caucasian, or Indic languages

## When to avoid
- you need a permissive commercial license - models are CC BY-NC 4.0
- you need state-of-the-art English TTS quality
- you need to train or fine-tune models yourself

## Facets
- artifact type: dataset
- maturity: active
- function: tts, speech-recognition, machine-learning
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: pretrained-models, pytorch, torch-hub, text-to-speech, multilingual, ssml, cpu-inference, natural-language-processing, gpu

## Member repositories
- snakers4/silero-models (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.876817+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:48:19.993449+00:00, confidence not recorded.
  - readme: https://github.com/snakers4/silero-models (fetched 2026-08-28T04:09:34.876817+00:00, sha 4c01eca62fc1)
- Data as of 2026-08-30T08:39:29.467469+00:00.