{"data":{"slug":"yan5xu-ququ","name":"ququ","tagline":"Open-source free Wispr Flow alternative integrating FunASR local models and configurable large language models for next-generation Chinese desktop voice workflow","github_url":"https://github.com/yan5xu/ququ","owner":"yan5xu","repo":"ququ","owner_avatar_url":"https://avatars.githubusercontent.com/u/5762066?v=4","primary_language":"JavaScript","stars":2251,"forks":230,"topics":["ai-text-processing","chinese-speech-recognition","electron-app","funasr","local-processing","open-source","privacy-first","speech-to-text","voice-dictation","wispr-flow-alternative"],"archived":false,"github_pushed_at":"2025-10-08T04:41:18+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/yan5xu-ququ","markdown_url":"https://www.graphcanon.com/tools/yan5xu-ququ.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/yan5xu-ququ","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=yan5xu-ququ","description":"开源免费的 Wispr Flow 替代方案 | 集成FunASR本地模型和可配置大语言模型的下一代中文桌面语音工作流","homepage_url":null,"license":"Other","open_issues":51,"watchers":15,"ai_summary":"Offers a speech-to-text solution tailored for Chinese users with an emphasis on privacy, using electron-app framework and incorporating FunASR for processing.","readme_excerpt":"# powershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"","github_created_at":"2025-09-20T06:26:58+00:00","created_at":"2026-07-11T12:17:23.02302+00:00","updated_at":"2026-07-30T18:00:05.27898+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"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-text-processing","name":"ai-text-processing"},{"slug":"chinese-speech-recognition","name":"chinese-speech-recognition"},{"slug":"electron-app","name":"electron-app"},{"slug":"funasr","name":"funasr"},{"slug":"local-processing","name":"local-processing"},{"slug":"open-source","name":"open-source"},{"slug":"privacy-first","name":"privacy-first"},{"slug":"speech-to-text","name":"speech-to-text"}],"trust":{"provenance":{"is_fork":false,"github_id":1060564078,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-30T18:00:04.093Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":295,"last_release_at":"2025-09-22T16:32:02Z"},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:17:27.350Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-07-30T18:00:04.644Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-07-30T18:00:04.644Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-07-30T18:00:04.644Z"},"languages":{"value":["javascript","python"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-07-30T18:00:04.644Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-07-30T18:00:04.644Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use with no paid options mentioned. Open-source license allows free modifications and distribution for privacy-focused projects."},"requirements":{"min_ram_gb":2,"requires_docker":false},"constraints":{"min_ram_gb":2,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you require a tool specifically tailored to the Chinese language in a desktop environment.","For projects needing enhanced privacy controls over voice recognition data.","If your development involves Electron-app framework-based applications that need speech-to-text capabilities."],"when_not_to_use":["In environments where real-time processing speed is prioritized over local model accuracy and privacy benefits.","When the project requires support for multiple languages beyond Chinese.","For integration into mobile apps, as ququ focuses on desktop workflows."],"source":"enrich:decision_facts","observed_at":"2026-07-17T08:21:37.386Z"},"constraint_facets":{"min_ram_gb":2,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use with no paid options mentioned. Open-source license allows free modifications and distribution for privacy-focused projects."},{"label":"Requirements","value":"Min 2 GB RAM"},{"label":"Adopt for","value":"ququ is an open-source speech-to-text solution that focuses on privacy and Chinese-speaking users, integrating with FunASR for local processing and configurable large language models."}]}}