{"id":45461973,"url":"https://github.com/panda850819/murmur-voice","last_synced_at":"2026-03-10T08:14:15.572Z","repository":{"id":338206939,"uuid":"1156859080","full_name":"panda850819/murmur-voice","owner":"panda850819","description":"Privacy-first voice-to-text for macOS and Windows. Local Whisper (Metal/CUDA) or Groq cloud, with LLM post-processing. Built with Rust + Tauri 2.","archived":false,"fork":false,"pushed_at":"2026-02-28T02:14:07.000Z","size":3571,"stargazers_count":12,"open_issues_count":11,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-28T11:49:01.936Z","etag":null,"topics":["dictation","macos","privacy","rust","speech-to-text","tauri","transcription","voice-to-text","whisper","windows"],"latest_commit_sha":null,"homepage":"https://github.com/panda850819/murmur-voice/releases","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/panda850819.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-13T06:08:36.000Z","updated_at":"2026-02-28T06:23:50.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/panda850819/murmur-voice","commit_stats":null,"previous_names":["panda850819/murmur-voice"],"tags_count":8,"template":false,"template_full_name":null,"purl":"pkg:github/panda850819/murmur-voice","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/panda850819%2Fmurmur-voice","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/panda850819%2Fmurmur-voice/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/panda850819%2Fmurmur-voice/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/panda850819%2Fmurmur-voice/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/panda850819","download_url":"https://codeload.github.com/panda850819/murmur-voice/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/panda850819%2Fmurmur-voice/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30327855,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T05:25:20.737Z","status":"ssl_error","status_checked_at":"2026-03-10T05:25:17.430Z","response_time":106,"last_error":"SSL_read: 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":["dictation","macos","privacy","rust","speech-to-text","tauri","transcription","voice-to-text","whisper","windows"],"created_at":"2026-02-22T08:08:12.010Z","updated_at":"2026-03-10T08:14:15.554Z","avatar_url":"https://github.com/panda850819.png","language":"Rust","funding_links":["https://buymeacoffee.com/pdzeng"],"categories":[],"sub_categories":[],"readme":"# Murmur\n\n[![Release](https://img.shields.io/github/v/release/panda850819/murmur-voice?include_prereleases\u0026style=flat-square)](https://github.com/panda850819/murmur-voice/releases)\n[![CI](https://img.shields.io/github/actions/workflow/status/panda850819/murmur-voice/ci.yml?branch=main\u0026style=flat-square\u0026label=CI)](https://github.com/panda850819/murmur-voice/actions/workflows/ci.yml)\n[![License](https://img.shields.io/github/license/panda850819/murmur-voice?style=flat-square)](LICENSE)\n[![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Windows-blue?style=flat-square)]()\n\n**[English](README.md)** | **[繁體中文](README.zh-TW.md)**\n\n\u003ca href=\"https://buymeacoffee.com/pdzeng\"\u003e\u003cimg src=\"https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png\" height=\"48\" width=\"173\" alt=\"Buy Me A Coffee\" /\u003e\u003c/a\u003e\n\n\u003e Your voice, unheard by others.\n\nPrivacy-first voice-to-text for macOS and Windows, built with Rust.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/screenshot-settings.png\" width=\"360\" alt=\"Settings\" /\u003e\n  \u003cimg src=\"assets/screenshot-recording.png\" width=\"360\" alt=\"Recording\" /\u003e\n\u003c/p\u003e\n\n## What is Murmur?\n\nMurmur is a voice dictation tool that transcribes your speech and inserts polished text at your cursor position -- in any app. It supports both local (on-device) and cloud transcription, with optional LLM post-processing to clean up filler words, fix punctuation, and convert Simplified Chinese to Traditional Chinese.\n\n## Features\n\n- **Push-to-Talk** -- Hold a modifier key to speak, release to insert text\n- **Toggle Mode** -- Press once to start recording, press again to stop (with 5-min auto-stop and debounce protection)\n- **Custom Hotkey** -- Single modifier key or combo (e.g. Option+Z, Control+Space) with two-phase recording\n- **Dual Engine** -- Local Whisper (Metal GPU) or Groq cloud API\n- **Multi-Provider LLM** -- Groq (cloud), Ollama (local), or any OpenAI-compatible endpoint for text enhancement\n- **Fully Offline Mode** -- Local Whisper + Ollama for complete privacy (no data leaves your machine)\n- **LLM Post-Processing** -- Clean up filler words, add punctuation, Simplified-to-Traditional Chinese conversion\n- **Smart Clipboard** -- Auto-pastes when a text field is focused; copies to clipboard only when no text input is detected (e.g. on Desktop)\n- **App-Aware Style** -- Automatically adjusts output tone based on the active app (e.g. formal in Slack, technical in VS Code)\n- **Personal Dictionary** -- Add custom terms to improve transcription accuracy; inline dictionary chips appear in real-time while editing\n- **Transcription Preview** -- Floating preview window with copy button, editable text, character count, and detected app name\n- **Live Preview** -- See partial transcription while you speak (local engine only)\n- **Mixed-Language Support** -- English words in mixed CJK-English speech are preserved as-is (never translated)\n- **15 Languages** -- Auto-detect or manually select from 15 supported languages\n- **Cross-Platform** -- macOS and Windows support with platform-native hotkey and app detection\n- **System-wide** -- Works in any text field across all apps\n- **Lightweight** -- Tauri-based, ~30-50MB vs 200MB+ Electron apps\n- **Open Source** -- Fully auditable, no telemetry, no tracking\n\n## Download\n\nDownload the latest release from the [Releases page](https://github.com/panda850819/murmur-voice/releases).\n\n| Platform | File | Notes |\n|----------|------|-------|\n| macOS (Apple Silicon) | `.dmg` | Requires [quarantine removal](#macos-murmur-voice-is-damaged-and-cant-be-opened) |\n| Windows | `.exe` / `.msi` | CPU-only, works on all hardware |\n| Windows (NVIDIA GPU) | `-cuda.exe` / `-cuda.msi` | GPU-accelerated via CUDA |\n\n## How It Works\n\n```\nHotkey -\u003e Record (cpal) -\u003e Transcribe (Whisper) -\u003e LLM Clean-up (optional) -\u003e Smart Clipboard (paste or copy-only)\n```\n\n**Each recording triggers at most 2 API calls** (when using Groq): one for Whisper transcription, one for LLM post-processing.\n\n## Setup Guide\n\n### 1. Install \u0026 Run\n\n```bash\ngit clone https://github.com/panda850819/murmur-voice.git\ncd murmur-voice\npnpm install\npnpm tauri dev\n```\n\n### 2. First Launch\n\nOn first launch, Murmur will guide you through:\n1. Granting **Microphone** and **Accessibility** permissions\n2. Choosing a transcription engine (Local or Groq)\n3. Setting your Push-to-Talk key\n\nIf you choose the local engine, the Whisper model (~1.5GB) will download automatically on your first recording.\n\n### 3. Transcription Engine\n\n| Engine | Speed | Quality | Privacy | Setup |\n|--------|-------|---------|---------|-------|\n| **Local (Whisper)** | ~1-3s | Good | Audio stays on device | Model auto-downloads on first use (~1.5GB) |\n| **Groq API** | \u003c1s | Good | Audio sent to Groq servers | Free API key ([get one below](#getting-a-groq-api-key)) |\n\nTo switch engines: **Settings \u003e Transcription \u003e Engine**\n\n#### Getting a Groq API Key\n\n1. Go to [console.groq.com](https://console.groq.com) and sign up (Google/GitHub login supported)\n2. Navigate to **API Keys** in the left sidebar\n3. Click **Create API Key**, give it a name (e.g. \"murmur\")\n4. Copy the key (starts with `gsk_`) and paste it into Murmur's settings\n\nGroq's free tier includes generous rate limits for personal use. The same API key is used for both Whisper transcription and LLM post-processing.\n\n### 4. LLM Post-Processing (Recommended)\n\nChoose a provider for AI text enhancement:\n\n| Provider | Speed | Privacy | Setup |\n|----------|-------|---------|-------|\n| **Groq** | Fast | Cloud | Free API key from [console.groq.com](https://console.groq.com) |\n| **Ollama** | Varies | Local | Install [Ollama](https://ollama.com), pull a model |\n| **Custom** | Varies | Varies | Any OpenAI-compatible endpoint |\n\nWhat it does:\n- Removes filler words (um, uh, etc.)\n- Removes false starts and self-corrections\n- Adds proper punctuation (full-width for Chinese, half-width for English)\n- Converts Simplified Chinese to Traditional Chinese (Taiwan standard)\n- Adds spaces between Chinese and English text\n- Formats lists and paragraphs when appropriate\n\nTo enable: **Settings \u003e AI Processing \u003e LLM Post-Processing**\n\n### 5. Personal Dictionary\n\nAdd frequently used terms (names, jargon, acronyms) to improve transcription accuracy. These are injected into Whisper's initial prompt.\n\nTo configure: **Settings \u003e Transcription \u003e Dictionary** (type a term, press Enter to add)\n\n### 6. App-Aware Style\n\nWhen enabled, Murmur detects the foreground app and adjusts the LLM output tone:\n\n| App | Style |\n|-----|-------|\n| Slack, Discord, LINE, Telegram | Casual |\n| VS Code, Terminal, Cursor | Technical |\n| Pages, Word, Google Docs | Formal |\n| Others | Default (natural) |\n\nTo enable: **Settings \u003e AI Processing \u003e App-Aware Style**\n\n## Recommended Settings\n\nFor the best experience with Chinese dictation:\n\n| Setting | Value | Why |\n|---------|-------|-----|\n| Engine | **Groq** | Fastest transcription (\u003c1s) |\n| Language | **Mandarin Chinese** | More accurate than Auto for Chinese |\n| LLM Post-Processing | **On** | Cleans up filler words + Traditional Chinese |\n| LLM Model | **Llama 3.3 70B** | Best quality for Chinese text processing |\n| App-Aware Style | **On** | Adapts tone to context |\n\n## Tech Stack\n\n| Component | Technology | Purpose |\n|-----------|-----------|---------|\n| App Framework | Tauri 2 | Lightweight desktop app |\n| Audio Capture | cpal | Microphone input -\u003e 16kHz mono |\n| Speech-to-Text | whisper-rs / Groq API | Local or cloud transcription |\n| LLM Processing | Groq / Ollama / Custom | Text cleanup and formatting |\n| Hotkey Detection | CGEventTap / SetWindowsHookEx | Global hotkey listener (modifier or modifier+key combo) |\n| Text Insertion | arboard + rdev | Clipboard write + Cmd+V / Ctrl+V simulation |\n| App Detection | NSWorkspace / Win32 API | Foreground app detection (per-platform) |\n\n## Requirements\n\n### macOS\n- macOS 12.0+ (Apple Silicon recommended for local Whisper)\n- Microphone permission\n- Accessibility permission (for global hotkey + text insertion)\n\n### Windows\n- Windows 10+\n- Microphone permission\n\n### Both Platforms\n- Groq API key (free, for cloud engine and Groq LLM) or Ollama (for local LLM)\n\n## FAQ\n\n### macOS: \"Murmur Voice is damaged and can't be opened\"\n\nThis happens because the app is not signed with an Apple Developer certificate. macOS Gatekeeper quarantines unsigned apps by default. To fix:\n\n1. Move Murmur Voice to `/Applications`\n2. Open Terminal and run:\n   ```bash\n   xattr -d com.apple.quarantine /Applications/Murmur\\ Voice.app\n   ```\n3. Open the app normally\n\n### Windows: Which version should I download?\n\n| Your GPU | Download | Why |\n|----------|----------|-----|\n| NVIDIA (with CUDA drivers) | `-cuda` version | GPU-accelerated transcription, much faster |\n| AMD / Intel / integrated | Standard version | CPU transcription, works on all hardware |\n| Not sure | Standard version | Always works, just slower for local engine |\n\n### Why is the app unsigned?\n\nMurmur is a free, open-source project. Apple Developer Program costs $99/year. Code signing may be added in the future, but for now the workaround above is required on macOS.\n\n## Privacy\n\nMurmur was born from a security audit of a commercial voice-to-text app that was found to:\n- Capture browser URLs and window titles\n- Monitor all keystrokes via CGEventTap\n- Send application context to remote servers\n- Include session recording analytics (Microsoft Clarity)\n\nMurmur does none of this. When using the **local engine**, your audio never leaves your machine. When using **Groq**, audio is sent only to Groq's API for transcription -- no other data is collected or transmitted.\n\n## Donate\n\nIf you find Murmur useful, consider supporting the project:\n\n\u003ca href=\"https://buymeacoffee.com/pdzeng\"\u003e\u003cimg src=\"https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png\" height=\"48\" width=\"173\" alt=\"Buy Me A Coffee\" /\u003e\u003c/a\u003e\n\n**Crypto:**\n\n| Network | Address |\n|---------|---------|\n| EVM (Ethereum, Base, etc.) | `0x9ae8954201b2fce97b124887e415df02e8e06a8d` |\n| Solana | `Eod4VqvMmmMnY3EinN6Zo5xzt9Wq5S2dFZutob1VBvMf` |\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpanda850819%2Fmurmur-voice","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpanda850819%2Fmurmur-voice","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpanda850819%2Fmurmur-voice/lists"}