{"data":{"slug":"open-less-openless","name":"openless","tagline":"AI-polished text from voice input for macOS and Windows","github_url":"https://github.com/Open-Less/openless","owner":"Open-Less","repo":"openless","owner_avatar_url":"https://avatars.githubusercontent.com/u/283287307?v=4","primary_language":"Rust","stars":2881,"forks":252,"topics":["ai-prompt","asr","dictation","linux","llm","macos","open-source","prompt-engineering","rust","speech-to-text","tauri","typeless","typeless-alternative","voice-input","windows","wispr-flow-alternative"],"archived":false,"github_pushed_at":"2026-07-22T00:52:10+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/open-less-openless","markdown_url":"https://www.graphcanon.com/tools/open-less-openless.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/open-less-openless","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=open-less-openless","description":"Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字)","homepage_url":"https://github.com/appergb/openless","license":"MIT","open_issues":34,"watchers":7,"ai_summary":"A rust-based open-source tool that converts spoken words into polished text across applications on macOS and Windows.","readme_excerpt":"## From tool to infrastructure\n\nAdvanced systems all do the same thing: **they turn today's communication into tomorrow's default rules.** The Internet won not because HTTP was faster, but because no one negotiates how data is transmitted anymore. Git won not because the code was better, but because teams stopped coordinating versions every day. Stripe won not because payments were faster, but because developers stopped coordinating with banks.\n\nWhat OpenLess does is not \"faster dictation\" — it **eliminates every act of coordination between a thought and clean text.** Turning what's in your head into usable text used to mean deciding, over and over: what tone for this one? how is that name spelled? which input field, copy or paste? where does the model's key live, and who has access? OpenLess **sediments** those repeated negotiations, layer by layer, into defaults:\n\n- **Tone** sediments into a **style pack** — named, switchable, live at a keystroke, never re-decided.\n- **Proper nouns** sediment into **dictionary hotwords** — recognized by the ASR, hinted to the polish model, never re-corrected.\n- **Where text lands** sediments into a **single insertion protocol** — hold → speak → it appears at the cursor, with an automatic clipboard fallback.\n- **Model and credentials** sediment into the **OS vault** — authorized once at launch, never renegotiated.\n\nThat is what **authorizing the infrastructure once, at launch** means: on first run you grant the microphone, accessibility, and cloud credentials exactly once; from that moment, \"speak → clean text at the cursor\" is no longer a negotiation you run each time, but a default protocol you can forget is even there. Judge OpenLess not by how much faster it is, but by how much **coordination it removes.**\n\n---\n\n## Download & install (end users)\n\nGo to [Releases](../../releases) and download:\n\n- **macOS**: `OpenLess_<version>_aarch64.dmg` (Apple Silicon) or `OpenLess_<version>_x64.dmg` (Intel). Open it, drag the app to `/Applications`, **then run the following once in Terminal to bypass the Gatekeeper \"damaged\" warning** (the build is ad-hoc signed, not Apple-notarized):\n  ```bash\n  xattr -cr /Applications/OpenLess.app\n  ```\n- **Windows**: `OpenLess_<version>_x64-setup.exe` — run the installer.\n- **Android** (release APKs on GitHub Release; debug APKs via Actions artifacts):\n  - **Phones (recommended)**: `OpenLess_<version>_arm64-v8a.apk`\n  - **Older 32-bit ARM**: `OpenLess_<version>_armeabi-v7a.apk`\n  - **64-bit emulator**: `OpenLess_<version>_x86_64.apk`\n  - **32-bit emulator**: `OpenLess_<version>_x86.apk`\n  - In-app updates (Settings → About) use `latest-android-{arch}.json` manifests; Beta users join Beta in Advanced settings.\n  - Debug smoke builds: `OpenLess-android-debug-{abi}-*.apk` from workflow_dispatch artifacts.\n  - If unsure, run `adb shell getprop ro.product.cpu.abi` and pick the matching APK.\n- **macOS (Homebrew)**:\n  ```bash\n  brew tap Open-Less/openless https://github.com/Open-Less/openless\n  brew install --cask openless\n  xattr -cr /Applications/OpenLess.app\n\n  # Upgrade to the latest version\n  brew update && brew upgrade openless\n  ```\n\nOn first launch, grant the permissions the app requests.\n\n**macOS:**\n1. Grant Microphone access.\n2. Grant Accessibility access.\n3. **Quit and reopen the app** — Accessibility only takes effect after a restart.\n4. Open Settings and fill in your Volcengine ASR + Ark credentials.\n\n**Windows:**\n1. Grant Microphone access when prompted.\n2. Open Settings → Permissions to verify the global hotkey listener is active.\n3. Fill in your Volcengine ASR + Ark credentials in Settings.\n\nFor the full end-user walkthrough, see [USAGE.md](USAGE.md).\n\n---\n\n## License\n\nOpenLess is released under the [MIT License](LICENSE).","github_created_at":"2026-04-27T07:25:49+00:00","created_at":"2026-07-11T11:58:20.542119+00:00","updated_at":"2026-07-28T06:00:49.66188+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"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-prompt","name":"ai-prompt"},{"slug":"asr","name":"asr"},{"slug":"dictation","name":"dictation"},{"slug":"linux","name":"linux"},{"slug":"llm","name":"llm"},{"slug":"macos","name":"macos"},{"slug":"open-source","name":"open-source"},{"slug":"prompt-engineering","name":"prompt-engineering"}],"trust":{"provenance":{"is_fork":false,"github_id":1222252809,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-28T06:00:48.922Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":6,"last_release_at":"2026-07-15T09:35:35Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:58:21.939Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-28T06:00:49.360Z"},"languages":{"value":["rust"],"source":"github.language","observed_at":"2026-07-28T06:00:49.360Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-28T06:00:49.360Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need an all-in-one solution for converting spoken words into polished written text across various applications without leaving the current app environment.","Your workflow benefits from integrating with tauri, a framework for building cross-platform desktop apps, as Openless is built specifically to work well within this ecosystem."],"when_not_to_use":["You require extensive customization options for AI text polishing, as Openless offers limited user-tuning settings compared to some competitors.","Your operating system is Linux; while it's listed under topics, the tool is explicitly developed and supported for macOS and Windows only."],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:05:33.343Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Openless is a Rust-based open-source tool that offers AI-polished text output from voice input for users on macOS and Windows platforms."}]}}