{"id":46253745,"url":"https://github.com/sebsto/wispr","last_synced_at":"2026-04-17T12:01:38.069Z","repository":{"id":341148890,"uuid":"1168786118","full_name":"sebsto/wispr","owner":"sebsto","description":"Privacy-first voice dictation for macOS — powered by on-device Whisper AI. No cloud, no tracking.","archived":false,"fork":false,"pushed_at":"2026-04-10T08:13:43.000Z","size":11932,"stargazers_count":85,"open_issues_count":4,"forks_count":10,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-10T09:03:52.955Z","etag":null,"topics":["accessibility","local-first","macos","menubar-app","privacy","speech-to-text","swift","swiftui","voice-dictation","whisper"],"latest_commit_sha":null,"homepage":"https://wispr.stormacq.com","language":"Swift","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sebsto.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-27T19:49:25.000Z","updated_at":"2026-04-10T08:13:48.000Z","dependencies_parsed_at":null,"dependency_job_id":"7a62f7e3-a4cc-451e-9609-6e8ae88d01ce","html_url":"https://github.com/sebsto/wispr","commit_stats":null,"previous_names":["sebsto/wispr"],"tags_count":23,"template":false,"template_full_name":null,"purl":"pkg:github/sebsto/wispr","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sebsto%2Fwispr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sebsto%2Fwispr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sebsto%2Fwispr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sebsto%2Fwispr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sebsto","download_url":"https://codeload.github.com/sebsto/wispr/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sebsto%2Fwispr/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31928229,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T10:35:34.458Z","status":"ssl_error","status_checked_at":"2026-04-17T10:35:09.472Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["accessibility","local-first","macos","menubar-app","privacy","speech-to-text","swift","swiftui","voice-dictation","whisper"],"created_at":"2026-03-03T23:06:30.584Z","updated_at":"2026-04-17T12:01:38.050Z","avatar_url":"https://github.com/sebsto.png","language":"Swift","readme":"# Wispr\n\nA macOS menu bar app for local speech-to-text transcription powered by [OpenAI Whisper](https://github.com/openai/whisper) and [NVIDIA Parakeet](https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/asr/intro.html).\n\nWispr runs entirely on-device — your audio never leaves your Mac.\n\n## Features\n\n- **Hotkey-triggered dictation** — press a shortcut to start/stop recording, transcribed text is inserted at the cursor\n- **Dual engine architecture** — choose between OpenAI Whisper and NVIDIA Parakeet models through a unified interface\n- **Multiple models** — Whisper Tiny (~75 MB) to Large v3 (~3 GB), Parakeet V3 (~400 MB), and Realtime 120M (~150 MB)\n- **Low-latency streaming** — Parakeet Realtime 120M provides end-of-utterance detection for near-instant results (English)\n- **Model management** — download, activate, switch, and delete models from a single UI\n- **Multi-language support** — Whisper supports 90+ languages, Parakeet V3 supports 25 languages\n- **Menu bar native** — lives in your menu bar, stays out of the way\n- **Onboarding flow** — guided setup for permissions, model selection, and a test dictation\n- **Accessibility-first** — full keyboard navigation, VoiceOver support, and high-contrast mode\n\n## Models\n\n| Model | Engine | Size | Streaming | Languages | Notes |\n|-------|--------|------|-----------|-----------|-------|\n| Tiny | Whisper | ~75 MB | No | 90+ | Fastest, lower accuracy |\n| Base | Whisper | ~140 MB | No | 90+ | Good balance for quick tasks |\n| Small | Whisper | ~460 MB | No | 90+ | Solid general-purpose |\n| Medium | Whisper | ~1.5 GB | No | 90+ | High accuracy |\n| Large v3 | Whisper | ~3 GB | No | 90+ | Best Whisper accuracy |\n| Parakeet V3 | Parakeet | ~400 MB | No | 25 | Fast, high accuracy, multilingual |\n| Realtime 120M | Parakeet | ~150 MB | Yes | English | Low-latency with end-of-utterance detection |\n\n## Installation\n\n### Homebrew (Recommended)\n\n```bash\nbrew tap sebsto/macos\nbrew install wispr\n```\n\n### Building from Source\n\nRequires macOS 15.0+ and Xcode 16+\n\n1. Clone the repo\n2. Open `wispr.xcodeproj` in Xcode\n3. Build and run (⌘R)\n4. Follow the onboarding flow to grant permissions and download a model\n\n### Xcode 26.4 build fix\n\n~~Previously, Xcode 26.4 required a manual patch to FluidAudio's `AsrManager`\nfor Swift 6 concurrency compliance. This is no longer needed — FluidAudio\ndropped its `swift-transformers` dependency (removing the version conflict with\nWhisperKit) and resolved the concurrency issue in their latest release\n([FluidInference/FluidAudio#448](https://github.com/FluidInference/FluidAudio/issues/448)).\nNo workaround is required; the project builds cleanly on Xcode 26.4.~~\n\nSee also: [argmaxinc/WhisperKit#451](https://github.com/argmaxinc/WhisperKit/issues/451).\n\n## Requirements\n\n- macOS 15.0+\n- Microphone permission\n\n## Architecture\n\n| Layer | Path | Description |\n|-------|------|-------------|\n| Models | `wispr/Models/` | Data types — model info, permissions, app state, errors |\n| Services | `wispr/Services/` | Core logic — audio engine, Whisper/Parakeet integration, hotkey monitoring, settings |\n| UI | `wispr/UI/` | SwiftUI views — menu bar, recording overlay, settings, onboarding |\n| Utilities | `wispr/Utilities/` | Logging, theming, SF Symbols, preview helpers |\n\nThe app uses a `CompositeTranscriptionEngine` that routes to the correct backend (WhisperService or ParakeetService) based on the selected model. Both engines conform to a shared `TranscriptionEngine` protocol, so switching between them is seamless.\n\n## License\n\nThis project is licensed under the Apache License 2.0. See [LICENSE](LICENSE) for details.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsebsto%2Fwispr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsebsto%2Fwispr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsebsto%2Fwispr/lists"}