{"id":50493441,"url":"https://github.com/AdrianScott/froshine","last_synced_at":"2026-06-18T22:00:45.716Z","repository":{"id":274379437,"uuid":"921320204","full_name":"AdrianScott/froshine","owner":"AdrianScott","description":"Speech-to-Text/Code using a fast local LLM, for Linux, uses Whisper","archived":false,"fork":false,"pushed_at":"2025-11-15T23:22:43.000Z","size":12,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-02-13T23:29:41.851Z","etag":null,"topics":["linux","tts","whisper","whisper-ai"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AdrianScott.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-01-23T18:30:42.000Z","updated_at":"2025-11-15T23:22:47.000Z","dependencies_parsed_at":"2025-07-27T13:19:33.670Z","dependency_job_id":"9330cf00-4640-43e9-90f3-eb81b5bc8dfb","html_url":"https://github.com/AdrianScott/froshine","commit_stats":null,"previous_names":["adrianscott/froshine"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AdrianScott/froshine","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianScott%2Ffroshine","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianScott%2Ffroshine/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianScott%2Ffroshine/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianScott%2Ffroshine/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdrianScott","download_url":"https://codeload.github.com/AdrianScott/froshine/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdrianScott%2Ffroshine/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34508867,"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":"2026-06-18T02:00:06.871Z","response_time":128,"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":["linux","tts","whisper","whisper-ai"],"created_at":"2026-06-02T05:00:36.702Z","updated_at":"2026-06-18T22:00:45.702Z","avatar_url":"https://github.com/AdrianScott.png","language":"Python","funding_links":[],"categories":["By Platform"],"sub_categories":["Linux"],"readme":"# Froshine VoiceCommander: Offline Voice-to-Text IDE Integration\n\nA privacy-focused voice command system for developers that works entirely offline. Uses OpenAI's Whisper AI locally on your machine for speech-to-text and WebRTC VAD for voice activity detection.\n\nCopyright 2025 Adrian Scott\n\n## Features \n\n- **100% Offline** - No audio data leaves your machine\n- **Real-time Monitoring** - Continuous voice input detection\n- **IDE Integration** - Direct text insertion into code editors\n- **Voice Commands** - Custom commands for common actions\n- **Command Word Support** - \"Flow\" prefix for commands (configurable)\n- **Pause/Unpause Transcription** - Say \"Flow pause\" or \"Flow unpause\"\n- **GPU Acceleration** - Optional CUDA support for faster processing\n\n## Requirements \n\n- Ubuntu 20.04+ (other Linux distros may work)\n- Python 3.8+\n- Working microphone or audio input device\n- xdotool (`sudo apt install xdotool` on Ubuntu/Debian)\n- PortAudio libraries (`sudo apt install portaudio19-dev`)\n\n## Installation \n\n1. Clone the repository\n2. Install dependencies:\n   ```bash\n   sudo apt install portaudio19-dev python3-dev xdotool ffmpeg\n   pip install -r requirements.txt\n   ```\n\n## Configuration \n\nFroshine can be configured using either:\n1. Command-line arguments\n2. Environment variables in a `.env` file\n3. System environment variables\n\nCommand-line arguments take precedence over environment variables.\n\n### Environment File\n\nCopy the example configuration file to create your own:\n```bash\ncp .env.example .env\n```\n\nThen edit `.env` to customize your settings. See `.env.example` for available options.\n\n### Audio Input Configuration\n\nBy default, Froshine uses your system's default audio input device. You can configure the audio input using environment variables:\n\n- `FROSHINE_AUDIO_DEVICE`: Specify a preferred audio device by name or index\n- `FROSHINE_LIST_DEVICES`: Set to \"1\" to list all available audio devices\n\nExamples:\n```bash\n# List all available audio devices\nFROSHINE_LIST_DEVICES=1 python voice_monitor_command_word.py\n\n# Use a specific device by name (partial match)\nFROSHINE_AUDIO_DEVICE=\"USB\" python voice_monitor_command_word.py\n\n# Use a specific device by index\nFROSHINE_AUDIO_DEVICE=\"2\" python voice_monitor_command_word.py\n```\n\n### Whisper Model Selection\n\nFroshine supports different Whisper models for speech recognition. You can choose the model using the `--model` or `-m` flag:\n\n```bash\n# Use the tiny English model (fastest, less accurate)\npython voice_monitor_command_word.py --model tiny.en\n\n# Use the large v3 model (slower, most accurate)\npython voice_monitor_command_word.py --model large-v3\n```\n\nAvailable models:\n- `tiny.en`: Tiny model (English only) - Fastest, lowest accuracy\n- `base.en`: Base model (English only) - Fast, basic accuracy\n- `small.en`: Small model (English only) - Default, good balance\n- `medium.en`: Medium model (English only) - Better accuracy, slower\n- `large-v3`: Large v3 model (All languages) - Best accuracy, slowest\n\nThe default model is `small.en`, which provides a good balance between speed and accuracy.\n\n## Usage with voice_monitor_command_word.py\n\nThis script continuously listens for voice input, transcribes it locally with Whisper, and types the transcribed text directly into your active window.\n\nStart the script:\n\n```bash\npython3 voice_monitor_command_word.py\n```\n\nBegin speaking: The system will detect speech and automatically type the transcribed text into your currently focused application.\n\n**Issue commands:**\n\n- Say \"Flow enter\" to press Enter.\n- Say \"Flow save file\" to simulate Ctrl+S.\n- Say \"Flow pause\" to stop typing text (commands still work).\n- Say \"Flow unpause\" to resume typing text.\n- Stop the script: Say \"Flow quit\", or press Ctrl+C in the terminal to exit.\n\n## Troubleshooting \n\n**Common Issues:**\n\n- **ALSA/JACK warnings**: Normal and safe to ignore\n- **No audio input**:\n  ```bash\n  # Check recording devices\n  arecord -l\n  ```\n- **Permission issues**:\n  ```bash\n  sudo usermod -a -G audio $USER\n  # Reboot after running\n  ```\n\n## Privacy \u0026 Security \n\n- All audio processing happens locally\n- No internet connection required\n- No tracking or data collection\n\n## Copyright\n\nCopyright 2025 Adrian Scott\n\n---\n\n**Acknowledgements**:\n\n- OpenAI Whisper AI model\n- WebRTC VAD for voice detection\n- PyAudio for audio capture\n\n````\nearly work in progress\n\n```bash\npython3 -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\n\nsudo apt install xdotool\n````\n\n```\nWINDOW_ID=$(xdotool search --name \"\\(Workspace\\) \\- Windsurf\")\necho $WINDOW_ID\nxdotool windowactivate --sync $WINDOW_ID; xdotool type --window $WINDOW_ID --delay 0 \"windsurf test froshine\"\n\n```\n\nCurrent mechanism is to start voice recorder, voice_to_ide.sh, then click in the field of Windsurf I want it to go into.\n\nNext step: voice detection to automatically fire up the recorder.\n\nAfter that: voice commands to choose window, and especially use Freepoprompt and o1-xml-parser to update files.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAdrianScott%2Ffroshine","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAdrianScott%2Ffroshine","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAdrianScott%2Ffroshine/lists"}