{"id":30740206,"url":"https://github.com/paladini/echo-transcribe","last_synced_at":"2026-05-20T05:09:53.450Z","repository":{"id":312959352,"uuid":"1043518427","full_name":"paladini/echo-transcribe","owner":"paladini","description":"An open-source desktop application for audio transcription using local AI. Private, secure and efficient.","archived":false,"fork":false,"pushed_at":"2025-09-03T02:47:41.000Z","size":3011,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-03T04:22:35.142Z","etag":null,"topics":["ai","free","open-source","speach-to-text","srt","srt-subtitles","transcribe","transcriber","whisper","whisper-ai"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","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/paladini.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":null,"authors":"AUTHORS.md","dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-08-24T03:06:37.000Z","updated_at":"2025-09-03T02:46:54.000Z","dependencies_parsed_at":"2025-09-03T04:22:37.797Z","dependency_job_id":"2da39d67-4167-4dff-837b-468ec747a379","html_url":"https://github.com/paladini/echo-transcribe","commit_stats":null,"previous_names":["paladini/echo-transcribe"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/paladini/echo-transcribe","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paladini%2Fecho-transcribe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paladini%2Fecho-transcribe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paladini%2Fecho-transcribe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paladini%2Fecho-transcribe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/paladini","download_url":"https://codeload.github.com/paladini/echo-transcribe/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paladini%2Fecho-transcribe/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273529550,"owners_count":25121828,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-03T02:00:09.631Z","response_time":76,"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":["ai","free","open-source","speach-to-text","srt","srt-subtitles","transcribe","transcriber","whisper","whisper-ai"],"created_at":"2025-09-04T00:00:47.563Z","updated_at":"2026-05-20T05:09:53.444Z","avatar_url":"https://github.com/paladini.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EchoTranscribe 🎙️\n\nAn open-source desktop application for audio transcription (Speech-To-Text) using local AI. Private, secure and efficient.\n\n\u003cimg width=\"1990\" height=\"1186\" alt=\"glam-shot-20250921-215530\" src=\"https://github.com/user-attachments/assets/4f5fce93-db55-4132-b7ef-014796a5c434\" /\u003e\n\n## ✨ Features\n\n- 🔒 **Completely Local**: Your audio files never leave your computer\n- 🤖 **Advanced AI**: Uses Whisper models for high-quality transcription\n- 🎨 **Modern Interface**: Clean and intuitive design with dark theme support\n- 📁 **Multiple Formats**: Support for MP3, WAV, FLAC, M4A, OGG and WebM\n- 🔄 **Batch Transcription**: Process multiple files simultaneously\n- 🌍 **Automatic Detection**: Automatically identifies audio language\n- ⏱️ **Precise Timestamps**: Word-level timestamps for detailed navigation\n- 💾 **Flexible Export**: Export to TXT, SRT or JSON\n- ⚙️ **Persistent Settings**: Dark/light theme and language saved between sessions\n- 🌐 **Multilingual**: Interface in English, Portuguese and Spanish (expandable)\n- ⚡ **Performance**: Optimized for speed and efficiency\n- 🖥️ **Cross-Platform**: Works on Windows, macOS and Linux\n\n## 🚀 Quick Start\n\n### Prerequisites\n\n- **Node.js** (version 18 or higher)\n- **Python** (version 3.8 or higher)\n- **Rust** (for Tauri compilation)\n\n#### Linux (Ubuntu/Debian)\n```bash\nsudo apt update\nsudo apt install libwebkit2gtk-4.0-dev libssl-dev libgtk-3-dev libayatana-appindicator3-dev librsvg2-dev libjavascriptcoregtk-4.0-dev\n```\n\n#### macOS\n```bash\n# Using Homebrew\nbrew install --cask xcode-command-line-tools\n```\n\n#### Windows\nOn Windows, you'll need Microsoft Visual Studio C++ Build Tools.\n\n### Development Installation\n\n1. **Clone the repository**\n```bash\ngit clone https://github.com/paladini/echo-transcribe.git\ncd echo-transcribe\n```\n\n2. **Install Node.js dependencies**\n```bash\nnpm install\n```\n\n3. **Setup Python environment and backend**\n```bash\n# The startup script will create venv and install dependencies automatically\nchmod +x start-backend.sh  # Linux/macOS only\n```\n\n4. **Run in development mode**\n\n**Option A: Quick Start (Recommended)**\n```bash\n# Terminal 1 - Start backend\n./start-backend.sh        # Linux/macOS\n# or\n./start-backend.bat       # Windows\n\n# Terminal 2 - Start frontend (Tauri v2)\nnpm run tauri dev\n```\n\n**Option B: Manual setup**\n```bash\n# Terminal 1 - Start backend\ncd src-tauri/backend\npython main.py\n\n# Terminal 2 - Start frontend\nnpm run tauri dev\n```\n\n5. **Verify setup**\n   - Backend API: http://localhost:8000/docs\n   - Frontend: Opens automatically in Tauri window\n\n\u003e 📖 **For detailed development setup**, see [DEVELOPMENT.md](DEVELOPMENT.md)\n\n### Production Installation\n\nDownload the latest version from [Releases](https://github.com/paladini/echo-transcribe/releases) for your operating system.\n\n## 🎯 How to Use\n\n1. **Select audio file(s)**\n   - Drag and drop one or multiple files to the designated area\n   - Or click to select files (maximum 10 at once)\n\n2. **Choose AI model**\n   - **Tiny/Base**: Fast, ideal for testing\n   - **Small**: Better quality, medium speed\n   - **Medium**: High quality, slower\n\n3. **Configure options**\n   - Leave automatic language detection enabled (recommended)\n   - Or manually specify the audio language\n\n4. **Start transcription**\n   - Click \"Start Transcription\"\n   - Track progress in real-time\n   - For batches, see progress for each file\n\n5. **View and edit results**\n   - See transcribed text for each file\n   - Navigate through word timestamps\n   - Edit text if necessary\n\n6. **Export results**\n   - Export individually or in batch\n   - Available formats: TXT, SRT, JSON\n\n7. **Configure application**\n   - Access settings to customize theme and language\n   - Your preferences are automatically saved for future sessions\n\n## 🛠️ Technologies\n\n- **Frontend**: React + TypeScript + Tailwind CSS\n- **Desktop**: Tauri (Rust)\n- **Backend**: FastAPI (Python)\n- **AI**: faster-whisper (OpenAI Whisper)\n- **UI Components**: Radix UI + shadcn/ui\n\n## 📋 Available Commands\n\n```bash\n# Development (Tauri v2)\nnpm run tauri dev        # Start Tauri v2 application in development mode\nnpm run dev             # Start frontend development server only (Vite)\n\n# Production (Tauri v2)\nnpm run build           # Build frontend\nnpm run tauri build     # Build complete application (generates executable)\n\n# Backend (Python)\ncd src-tauri/backend\npython main.py          # Start standalone backend server\n\n# Other useful commands\nnpm run preview         # Preview built frontend\nnpm run tauri --version # Check Tauri CLI version\n```\n\n### 🏗️ **Building and Running Executable**\n\nAfter running `npm run tauri build`, you can find and execute the generated files:\n\n```bash\n# Direct executable\n./src-tauri/target/release/echo-transcribe\n\n# AppImage (Recommended for distribution)\nchmod +x src-tauri/target/release/bundle/appimage/EchoTranscribe_0.1.0_amd64.AppImage\n./src-tauri/target/release/bundle/appimage/EchoTranscribe_0.1.0_amd64.AppImage\n\n# Install .deb package (Ubuntu/Debian)\nsudo dpkg -i src-tauri/target/release/bundle/deb/EchoTranscribe_0.1.0_amd64.deb\necho-transcribe  # Run from anywhere after installation\n\n# Install .rpm package (Red Hat/Fedora)\nsudo rpm -i src-tauri/target/release/bundle/rpm/EchoTranscribe-0.1.0-1.x86_64.rpm\n```\n\n## 🔧 Configuration\n\n### AI Models\n\nEcho-Transcribe automatically downloads AI models as needed. Models are stored in:\n\n- **Linux/macOS**: `~/.echo-transcribe/models/`\n- **Windows**: `%USERPROFILE%\\\\.echo-transcribe\\\\models\\\\`\n\n### Supported Formats\n\n| Format | Extension | Max Size |\n|--------|-----------|----------|\n| MP3    | .mp3      | 500MB    |\n| WAV    | .wav      | 500MB    |\n| FLAC   | .flac     | 500MB    |\n| M4A    | .m4a      | 500MB    |\n| OGG    | .ogg      | 500MB    |\n| WebM   | .webm     | 500MB    |\n\n## 🐛 Troubleshooting\n\n### Common Issues\n\n**Error: \"Load Failed\"**\n- This usually means the Python backend isn't running\n- Make sure Python 3.8+ is installed on your system\n- The application will automatically install Python dependencies on first run\n- If the problem persists, try:\n  1. Close and reopen the application\n  2. Check if port 8000 is available\n  3. Install dependencies manually: `cd src-tauri/backend \u0026\u0026 pip install -r requirements.txt`\n\n**Error: \"Model not found\"**\n- The model will be downloaded automatically on first run\n- Check your internet connection\n\n**Error: \"Unsupported file format\"**\n- Check if the file is in one of the supported formats\n- Try converting the file to MP3 or WAV\n\n**Application won't open on Linux**\n- Check if all system dependencies are installed\n- Run: `sudo apt install libwebkit2gtk-4.0-37`\n\n### Debug Logs\n\nApplication logs are located at:\n- **Linux/macOS**: `~/.echo-transcribe/logs/`\n- **Windows**: `%USERPROFILE%\\\\.echo-transcribe\\\\logs\\\\`\n\n## 🤝 Contributing\n\nContributions are very welcome! Please read our [Contributing Guide](CONTRIBUTING.md) to get started.\n\n### Local Development\n\n1. Fork the project\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add some amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## 📝 Roadmap\n\n- [x] **v0.1.0** ✅ **COMPLETED**\n  - [x] Batch transcription support\n  - [x] Automatic language detection\n  - [x] Precise word-level timestamps\n  - [x] Export to multiple formats (TXT, SRT, JSON)\n  - [x] Settings screen with persistence\n  - [x] Theme support (light/dark)\n  - [x] Localization system (EN/PT/ES)\n  \n- [ ] **v0.2.0**\n  - [ ] Support for more AI models\n  - [ ] Timestamp interface improvements\n  - [ ] Community language support\n\n- [ ] **Future Versions**\n  - [ ] Custom model training interface\n  - [ ] Complete REST API\n  - [ ] Audio streaming support\n  - [ ] Plugin marketplace\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n\n- [OpenAI](https://openai.com/) for the Whisper model\n- [Tauri](https://tauri.app/) for the desktop framework\n- [FastAPI](https://fastapi.tiangolo.com/) for the backend framework\n- [shadcn/ui](https://ui.shadcn.com/) for UI components\n\n## 📞 Support\n\n-  Issues: [GitHub Issues](https://github.com/paladini/echo-transcribe/issues)\n- 💬 Discussions: [GitHub Discussions](https://github.com/paladini/echo-transcribe/discussions)\n- 👤 Author: [github.com/paladini](https://github.com/paladini)\n\n---\n\n**EchoTranscribe** - Transforming audio to text with privacy and quality. 🎙️✨\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpaladini%2Fecho-transcribe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpaladini%2Fecho-transcribe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpaladini%2Fecho-transcribe/lists"}