{"data":{"slug":"snakers4-silero-models","name":"silero-models","tagline":"Silero Models provide simple access to pre-trained text-to-speech models","github_url":"https://github.com/snakers4/silero-models","owner":"snakers4","repo":"silero-models","owner_avatar_url":"https://avatars.githubusercontent.com/u/12515440?v=4","primary_language":"Jupyter Notebook","stars":6115,"forks":373,"topics":["armenian","azerbaijani","belarus","colab","georgian","kazakh","kyrgyz","pretrained-models","pytorch","russian","speech","speech-synthesis","speech-to-text","tajik","text-to-speech","torch-hub","tts","tts-models","ukrainian","uzbek"],"archived":false,"github_pushed_at":"2026-07-31T16:28:45+00:00","maintenance_label":"Steady","stars_delta_30d":85,"url":"https://www.graphcanon.com/tools/snakers4-silero-models","markdown_url":"https://www.graphcanon.com/tools/snakers4-silero-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/snakers4-silero-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=snakers4-silero-models","description":"Silero Models: pre-trained text-to-speech models made embarrassingly simple","homepage_url":null,"license":"Other","open_issues":12,"watchers":92,"ai_summary":"This repository offers pre-trained text-to-speech models for various languages via PyTorch Hub, pip installation, and manual caching methods.","readme_excerpt":"## Installation and Basics\n\nYou can basically use our models in 3 flavours:\n\n- Via PyTorch Hub: `torch.hub.load()`;\n- Via pip:  `pip install silero` and then `from silero import silero_tts`;\n- Via caching the required models and utils manually and modifying if necessary;\n\nModels are downloaded on demand both by pip and PyTorch Hub. If you need caching, do it manually or via invoking a necessary model once (it will be downloaded to a cache folder). Please see these [docs](https://pytorch.org/docs/stable/hub.html#loading-models-from-hub) for more information.\n\nPyTorch Hub and pip package are based on the same code. All of the `torch.hub.load` examples can be used with the pip package via this basic change:\n\n```python\nfrom silero import silero_tts\nmodel, example_text = silero_tts(language='ru',\n                                 speaker='v5_ru')\naudio = model.apply_tts(text=example_text)\n```","github_created_at":"2020-09-11T12:10:23+00:00","created_at":"2026-07-11T12:06:19.645902+00:00","updated_at":"2026-09-20T07:05:44.758763+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"armenian","name":"armenian"},{"slug":"azerbaijani","name":"azerbaijani"},{"slug":"belarus","name":"belarus"},{"slug":"colab","name":"colab"},{"slug":"georgian","name":"georgian"},{"slug":"kazakh","name":"kazakh"},{"slug":"kyrgyz","name":"kyrgyz"},{"slug":"pretrained-models","name":"pretrained-models"}],"trust":{"provenance":{"is_fork":false,"github_id":294685606,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:05:43.156Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":50,"last_release_at":"2026-06-04T05:33:28Z","stars_delta_30d":85,"open_issues_delta_30d":0},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:06:25.750Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:05:44.210Z"},"languages":{"value":["jupyter notebook","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T07:05:44.210Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T07:05:44.210Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need easy integration of text-to-speech functionalities in Jupyter Notebooks","Focus on supporting lesser-covered languages like Armenian or Azerbaijanian"],"when_not_to_use":["Require advanced customization of the speech synthesis process beyond provided options","Looking for a full end-to-end speech recognition (speech-to-text) solution, as this mainly focuses on text-to-speech"],"source":"enrich:decision_facts","observed_at":"2026-07-17T02:05:33.768Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Provides simple access to pre-trained text-to-speech models for various languages via PyTorch Hub, pip installation, and manual caching."}]}}