{"data":{"slug":"shivammehta25-matcha-tts","name":"Matcha-TTS","tagline":"Matcha-TTS is a fast TTS architecture with conditional flow matching","github_url":"https://github.com/shivammehta25/Matcha-TTS","owner":"shivammehta25","repo":"Matcha-TTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/9089131?v=4","primary_language":"Jupyter Notebook","stars":1358,"forks":216,"topics":["deep-learning","diffusion-model","diffusion-models","flow-matching","machine-learning","non-autoregressive","probabilistic","probabilistic-machine-learning","text-to-speech","tts","tts-api","tts-engines"],"archived":false,"github_pushed_at":"2026-08-31T22:29:48+00:00","maintenance_label":"Active","stars_delta_30d":19,"url":"https://www.graphcanon.com/tools/shivammehta25-matcha-tts","markdown_url":"https://www.graphcanon.com/tools/shivammehta25-matcha-tts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/shivammehta25-matcha-tts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=shivammehta25-matcha-tts","description":"[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching","homepage_url":"https://shivammehta25.github.io/Matcha-TTS/","license":"MIT","open_issues":34,"watchers":14,"ai_summary":"[ICASSP 2024] Matcha-TTS offers a method for fast text-to-speech generation using deep learning and diffusion models with non-autoregressive probabilistic techniques.","readme_excerpt":"## Installation\n\n1. Create an environment (suggested but optional)\n\n```\nconda create -n matcha-tts python=3.10 -y\nconda activate matcha-tts\n```\n\n2. Install Matcha TTS using pip or from source\n\n```bash\npip install matcha-tts\n```\n\nfrom source\n\n```bash\npip install git+https://github.com/shivammehta25/Matcha-TTS.git\ncd Matcha-TTS\npip install -e .\n```\n\n3. Run CLI / gradio app / jupyter notebook\n\n```bash","github_created_at":"2023-09-05T22:08:15+00:00","created_at":"2026-07-11T12:12:14.133129+00:00","updated_at":"2026-09-20T07:13:13.419822+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":"deep-learning","name":"deep-learning"},{"slug":"diffusion-models","name":"diffusion-models"},{"slug":"flow-matching","name":"flow-matching"},{"slug":"non-autoregressive","name":"non-autoregressive"},{"slug":"probabilistic-machine-learning","name":"probabilistic-machine-learning"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"tts-api","name":"tts-api"},{"slug":"tts-engines","name":"tts-engines"}],"trust":{"provenance":{"is_fork":false,"github_id":687727674,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:13:11.572Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":19,"last_release_at":"2024-08-09T16:34:46Z","stars_delta_30d":19,"open_issues_delta_30d":-1},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":103,"high_count":0,"last_scan_at":"2026-07-11T12:12:15.971Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:13:12.620Z"},"languages":{"value":["jupyter notebook","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T07:13:12.620Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T07:13:12.620Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you require rapid deployment of text-to-speech engines without autoregressive dependencies","For applications needing state-of-the-art ICASSP 2024 advancements in TTS technology"],"when_not_to_use":["If your project requires real-time adaptability to user input that necessitates autoregressive methods","In scenarios where licensing flexibility is not a priority, favoring proprietary systems with dedicated support"],"source":"enrich:decision_facts","observed_at":"2026-07-17T01:08:17.938Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Matcha-TTS employs non-autoregressive probabilistic techniques with deep learning for fast TTS generation."}]}}