{"id":46097352,"url":"https://github.com/saurabhav88/enviouswispr","last_synced_at":"2026-06-08T22:00:33.949Z","repository":{"id":339302619,"uuid":"1161274003","full_name":"saurabhav88/EnviousWispr","owner":"saurabhav88","description":"Free, sub-second on-device AI dictation for macOS. Dual engines (Whisper + Parakeet) on Apple Silicon, polished by Apple Intelligence. No cloud, no account, no subscription.","archived":false,"fork":false,"pushed_at":"2026-06-06T21:43:31.000Z","size":290414,"stargazers_count":8,"open_issues_count":78,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-06T22:18:33.927Z","etag":null,"topics":["accessibility","apple-silicon","coreml","dictation","macos","on-device-ai","open-source","parakeet","privacy","productivity","speech-to-text","swift","voice-typing","whisper"],"latest_commit_sha":null,"homepage":"https://enviouswispr.com","language":"Swift","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/saurabhav88.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":".github/CODEOWNERS","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":"2026-02-18T23:28:05.000Z","updated_at":"2026-06-06T21:43:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"0e4bfcd1-2c6f-4969-a0f2-562ad5d6fb8c","html_url":"https://github.com/saurabhav88/EnviousWispr","commit_stats":null,"previous_names":["saurabhav88/enviouswispr"],"tags_count":46,"template":false,"template_full_name":null,"purl":"pkg:github/saurabhav88/EnviousWispr","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saurabhav88%2FEnviousWispr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saurabhav88%2FEnviousWispr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saurabhav88%2FEnviousWispr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saurabhav88%2FEnviousWispr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/saurabhav88","download_url":"https://codeload.github.com/saurabhav88/EnviousWispr/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saurabhav88%2FEnviousWispr/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34082130,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","apple-silicon","coreml","dictation","macos","on-device-ai","open-source","parakeet","privacy","productivity","speech-to-text","swift","voice-typing","whisper"],"created_at":"2026-03-01T19:00:52.694Z","updated_at":"2026-06-08T22:00:33.943Z","avatar_url":"https://github.com/saurabhav88.png","language":"Swift","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/readme/icon.svg\" width=\"80\" alt=\"EnviousWispr icon\" /\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eEnviousWispr\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eTalk naturally. Paste perfectly.\u003c/strong\u003e\u003cbr/\u003e\n  Free, on-device AI dictation and speech-to-text for macOS.\u003cbr/\u003e\n  Powered by Apple Silicon. No cloud, no account, your voice never leaves your Mac.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/saurabhav88/EnviousWispr/releases/latest\"\u003e\u003cimg src=\"https://img.shields.io/github/v/release/saurabhav88/EnviousWispr?style=flat-square\u0026label=latest\u0026color=7c3aed\" alt=\"Latest Release\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/saurabhav88/EnviousWispr/releases/latest/download/EnviousWispr.dmg\"\u003e\u003cimg src=\"https://img.shields.io/badge/download-DMG-black?style=flat-square\" alt=\"Download DMG\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://enviouswispr.com\"\u003e\u003cimg src=\"https://img.shields.io/badge/web-enviouswispr.com-7c3aed?style=flat-square\" alt=\"Website\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://x.com/EnviousLabs\"\u003e\u003cimg src=\"https://img.shields.io/badge/follow-@EnviousLabs-black?style=flat-square\u0026logo=x\" alt=\"Follow on X\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/readme/hero.gif\" width=\"720\" alt=\"EnviousWispr hero - Talk naturally, paste perfectly\" /\u003e\n\u003c/p\u003e\n\n---\n\n## Demo\n\nhttps://github.com/user-attachments/assets/e636e1a0-a0d1-4f7c-be0a-b7c907c6d5ab\n\n## What is this?\n\nEnviousWispr is a free AI dictation app for macOS that runs entirely on-device. It uses Whisper and Parakeet speech-to-text models on Apple Silicon to transcribe your voice locally, polishes the output with an optional LLM, and pastes clean text into whatever app you're working in. Transcription is sub-second; with optional AI polish, the full hotkey-to-paste flow typically lands in around a second and a half.\n\nNo cloud. No account required. No subscription. No audio ever leaves your Mac. Works fully offline.\n\n## Why EnviousWispr?\n\n| | EnviousWispr | Cloud dictation services |\n|---|---|---|\n| **Privacy** | 100% on-device transcription | Audio uploaded to servers |\n| **Speed** | Sub-second transcription, paste-on-stop | Network round-trip latency |\n| **Models** | Parakeet v3 (NVIDIA NeMo) + WhisperKit (OpenAI Whisper) | Single vendor model |\n| **Polish** | Optional. Fully on-device (Apple Intelligence, Ollama) or bring-your-own-key cloud (GPT, Gemini) | Cloud polish, included in subscription |\n| **Cost** | Free. No account, no subscription | Monthly subscription |\n| **Works offline** | Yes, fully functional without internet | No |\n\n## How it works\n\n```\nPress hotkey  --\u003e  Record  --\u003e  Transcribe  --\u003e  Polish (optional)  --\u003e  Paste\n    ~0ms          live        ~400-800ms         ~200-500ms            instant\n```\n\n1. **Press your hotkey** from any app. Push-to-talk, toggle, or hands-free (double-press to lock for long-form), your choice.\n2. **Speak naturally.** Silero VAD detects when you stop talking and ends recording automatically.\n3. **On-device transcription.** Choose Parakeet v3 (fastest, 25 European languages) or WhisperKit (99 languages, with automatic language detection).\n4. **AI polish** (optional). Clean up grammar, punctuation, and formatting. Runs fully on-device with Apple Intelligence (macOS 26+) or Ollama, or in the cloud via OpenAI or Gemini with your own API key.\n5. **Text lands in your clipboard** and optionally auto-pastes into the active app.\n\n\u003e See the full interactive pipeline demo at [enviouswispr.com/how-it-works](https://enviouswispr.com/how-it-works)\n\n## Supported Models\n\n| Model | Best for | Languages | Disk space | Hardware |\n|---|---|---|---|---|\n| **Parakeet TDT v3** | Fastest dictation (default) | 25 European languages | ~460 MB | Apple Silicon |\n| **WhisperKit** (Whisper Large v3 Turbo) | Broadest language coverage and automatic language detection | 99 languages | ~1.6 GB | Apple Silicon |\n\nBoth models run entirely on-device using CoreML. First launch downloads and compiles the model; subsequent launches are instant.\n\n## Features\n\n- 🎙️ **Dual ASR engines** with [Parakeet v3](https://github.com/FluidInference/FluidAudio) (NVIDIA NeMo) and [WhisperKit](https://github.com/argmaxinc/argmax-oss-swift) (OpenAI Whisper)\n- ✨ **AI polish that respects your words** — strips filler words and false starts, fixes grammar and punctuation, formats numbers, dates, and URLs, and honors your custom vocabulary, all in your spoken language (never translated or rewritten)\n- 🔒 **Polish that can stay private** — run it fully on-device with Apple Intelligence (macOS 26+) or Ollama, or in the cloud via OpenAI GPT / Google Gemini with your own API key\n- 🌍 **Multilingual with automatic language detection** — speak in any supported language and EnviousWispr detects it, then offers to lock it in for faster, more accurate transcription\n- 😀 **Speak an emoji** — say the emoji's name followed by \"emoji\" (like \"thumbs up emoji\") and the glyph drops right in\n- ✋ **Voice Activity Detection** via Silero VAD — stops recording automatically when you stop talking\n- 📚 **Custom vocabulary** for names, brands, and technical terms the ASR might miss\n- ⌨️ **Global hotkey** with push-to-talk, toggle, and hands-free modes (double-press to lock for long-form dictation)\n- 📋 **Auto-paste** directly into the active app, or just copy to clipboard\n- 🕘 **Transcript history** for browsing, searching, and reviewing past dictations, with one-click re-polish to re-run AI cleanup on any past transcript\n- 🧭 **Menu bar native** with minimal footprint\n- 🔄 **Auto-updates** via Sparkle\n\n## Quick Start\n\n1. Download [EnviousWispr.dmg](https://github.com/saurabhav88/EnviousWispr/releases/latest/download/EnviousWispr.dmg) from the latest release\n2. Drag to Applications, launch\n3. Grant **Microphone**, **Accessibility**, and (on first paste fallback) **Automation** permissions when prompted\n4. Set your preferred hotkey in Settings \u003e Shortcuts\n5. Start talking\n\n**Optional:** Turn on AI polish in Settings \u003e AI Polish. Keep it fully on-device with Apple Intelligence (macOS 26+) or Ollama, or add an OpenAI or Gemini API key.\n\n## Requirements\n\n- macOS 14 (Sonoma) or later\n- Apple Silicon (M1 or newer)\n\n## Building from Source\n\n```bash\ngit clone https://github.com/saurabhav88/EnviousWispr.git\ncd EnviousWispr\nswift build            # compiles the Swift packages (dependencies resolve via SPM)\n```\n\nThe runnable `.app` is assembled by the Xcode build engine via Tuist, not by `swift build` — use `./scripts/build-dev-app.sh` for a local dev build, or the release path below. First build takes several minutes as ML models compile.\n\nFor a distributable `.app` bundle and DMG:\n\n```bash\n./scripts/build-release-dmg.sh \u003cversion\u003e\n```\n\nThe release build runs on the Xcode engine via Tuist, so it requires full Xcode (26+) plus mise and Tuist; set `CODESIGN_IDENTITY` to sign. Running the app itself requires macOS 14+.\n\n## Architecture\n\nThe app follows a pipeline state machine: **idle --\u003e recording --\u003e transcribing --\u003e polishing --\u003e complete**.\n\nKey design choices:\n- **Swift 6 strict concurrency** with full actor isolation\n- **Dual pipeline architecture** with deliberately separate Parakeet and WhisperKit backends (isolation is a feature, not tech debt)\n- **Heart \u0026 Limbs pattern** where the critical path (audio, ASR, paste) never fails, and features (polish, custom words, filler removal) degrade gracefully\n- **Local-first** with LLM polish as an opt-in enhancement using your own keys\n\n## Contributing\n\nContributions are welcome. Please open an issue to discuss significant changes before submitting a PR.\n\nThis project uses conventional commits: `feat(scope):`, `fix(scope):`, `refactor(scope):`.\n\n## Privacy\n\nEnviousWispr is built on a simple principle: **your voice is yours.**\n\n- Audio is captured, transcribed, and discarded locally. Nothing is uploaded, stored, or shared.\n- LLM polish (if enabled) can run entirely on your Mac with Apple Intelligence or a local Ollama model, so the polish step makes no network call. If you pick a cloud provider (OpenAI or Gemini), only text is sent (your transcript plus the polish instructions) using your own API key. Audio is never sent.\n- Anonymous product analytics (PostHog) can be disabled in Settings.\n- Crash reporting (Sentry) contains no transcript content, audio, or personal data.\n\n## Connect\n\n- **Website:** [enviouswispr.com](https://enviouswispr.com)\n- **X:** [@EnviousLabs](https://x.com/EnviousLabs)\n- **Email:** hello@enviouswispr.com\n\nBuilt by [Envious Labs](https://enviouslabs.co)\n\n## License\n\nEnviousWispr is source-available under the [Business Source License 1.1](LICENSE). You may view, fork, and modify the code for personal, non-commercial use. Commercial use requires a license from Envious Labs. The code converts to Apache 2.0 on March 10, 2030.\n\nFor commercial licensing inquiries: hello@enviouswispr.com\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaurabhav88%2Fenviouswispr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsaurabhav88%2Fenviouswispr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaurabhav88%2Fenviouswispr/lists"}