{"data":{"slug":"openwhispr-openwhispr","name":"openwhispr","tagline":"Voice-to-text dictation app with local and cloud models","github_url":"https://github.com/OpenWhispr/openwhispr","owner":"OpenWhispr","repo":"openwhispr","owner_avatar_url":"https://avatars.githubusercontent.com/u/254803777?v=4","primary_language":"JavaScript","stars":8381,"forks":1030,"topics":["ai","anthropic","cross-platform","gemini","groq","linux","macos","nvidia","open-source","openai","parakeet","speech-to-text","transcribe","whisper","windows"],"archived":false,"github_pushed_at":"2026-09-19T15:48:12+00:00","maintenance_label":"Very active","stars_delta_30d":3363,"url":"https://www.graphcanon.com/tools/openwhispr-openwhispr","markdown_url":"https://www.graphcanon.com/tools/openwhispr-openwhispr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openwhispr-openwhispr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openwhispr-openwhispr","description":"Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.","homepage_url":"https://openwhispr.com","license":"MIT","open_issues":339,"watchers":20,"ai_summary":"OpenWhispr is an open-source voice-to-text dictation application that supports both local Nvidia Parakeet/Whisper models and cloud-based options, ensuring privacy while being cross-platform compatible.","readme_excerpt":"## Quick start\n\n```bash\ngit clone https://github.com/OpenWhispr/openwhispr.git\ncd openwhispr\nnpm install\nnpm run dev\n```\n\nRequires Node.js 24+. See the [full documentation](https://docs.openwhispr.com/quickstart) for setup guides, platform-specific instructions, and build details.\n\n---\n\n## License\n\n[MIT](LICENSE) — free for personal and commercial use.","github_created_at":"2025-06-19T00:58:14+00:00","created_at":"2026-07-11T12:15:48.424648+00:00","updated_at":"2026-09-20T07:17:27.386519+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":"ai","name":"ai"},{"slug":"anthropic","name":"anthropic"},{"slug":"cross-platform","name":"cross-platform"},{"slug":"gemini","name":"gemini"},{"slug":"groq","name":"groq"},{"slug":"linux","name":"linux"},{"slug":"macos","name":"macos"},{"slug":"nvidia","name":"nvidia"}],"trust":{"provenance":{"is_fork":false,"github_id":1004647857,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:17:25.110Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":19,"days_since_push":0,"last_release_at":"2026-09-15T03:14:49Z","stars_delta_30d":3363,"open_issues_delta_30d":87},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:15:57.287Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T07:17:26.416Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:17:26.416Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T07:17:26.416Z"},"languages":{"value":["javascript","typescript"],"source":"github.language+package.json","observed_at":"2026-09-20T07:17:26.416Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T07:17:26.416Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Development and runtime environment requires Node.js version 24+.","Support for Nvidia Parakeet/Whisper models may require additional setup specific to the hardware and software configurations."],"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"requires_docker":false},"when_to_use":["When you require the use of Nvidia Parakeet/Whisper models for high accuracy in a local environment without internet dependency.","If your project needs a cross-platform tool that operates seamlessly on Windows, Linux, and macOS.","For projects sensitive to data privacy that prefer or mandate operating with local models rather than relying solely on cloud services."],"when_not_to_use":["When you have limited computational power on your device and rely heavily on cloud resources for processing voice-to-text without the overhead of managing local machine learning models.","If your application must work on platforms that are not supported by OpenWhispr, such as mobile devices or specialized operating systems."],"source":"enrich:decision_facts","observed_at":"2026-07-16T20:39:54.392Z"},"constraint_facets":{"min_ram_gb":4,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 4 GB RAM; Development and runtime environment requires Node.js version 24+.; Support for Nvidia Parakeet/Whisper models may require additional setup specific to the hardware and software configurations."},{"label":"Adopt for","value":"OpenWhispr is an open-source voice-to-text dictation application that features both local and cloud-based models, emphasizing privacy and cross-platform compatibility."}]}}