{"id":30701005,"url":"https://github.com/namuan/meeting-buddy","last_synced_at":"2026-05-03T21:31:07.404Z","repository":{"id":311961500,"uuid":"1044112549","full_name":"namuan/meeting-buddy","owner":"namuan","description":"Making meetings more productive, one transcription at a time! 🚀","archived":false,"fork":false,"pushed_at":"2025-09-14T20:03:17.000Z","size":5135,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-14T21:34:34.741Z","etag":null,"topics":["coach","meeting-notes","ollama","transcriber","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","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/namuan.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}},"created_at":"2025-08-25T07:50:37.000Z","updated_at":"2025-09-14T20:03:21.000Z","dependencies_parsed_at":"2025-08-28T03:04:52.376Z","dependency_job_id":"7f6fc9d7-8af2-4263-8418-cd6886205bb2","html_url":"https://github.com/namuan/meeting-buddy","commit_stats":null,"previous_names":["namuan/meeting-buddy"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/namuan/meeting-buddy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namuan%2Fmeeting-buddy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namuan%2Fmeeting-buddy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namuan%2Fmeeting-buddy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namuan%2Fmeeting-buddy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/namuan","download_url":"https://codeload.github.com/namuan/meeting-buddy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/namuan%2Fmeeting-buddy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32586186,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T06:36:36.687Z","status":"ssl_error","status_checked_at":"2026-05-03T06:36:09.306Z","response_time":103,"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":["coach","meeting-notes","ollama","transcriber","whisper"],"created_at":"2025-09-02T13:01:34.128Z","updated_at":"2026-05-03T21:31:07.398Z","avatar_url":"https://github.com/namuan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Meeting Buddy 🎤\n\nA real-time audio recording and transcription application with AI-powered analysis capabilities. Meeting Buddy helps you capture, transcribe, and analyze meetings or conversations using OpenAI Whisper for speech-to-text and local LLM integration via Ollama.\n\n![Demo](assets/demo.png)\n\n## Features\n\n- **Real-time Audio Recording**: Capture audio from any input device\n- **Live Transcription**: Convert speech to text using OpenAI Whisper\n- **AI Analysis**: Process transcriptions with local LLMs via Ollama\n\n## Requirements\n\n- Python 3.10 (specifically, not 3.11+)\n- PyQt6 for the GUI\n- PyAudio for audio recording\n- OpenAI Whisper for transcription\n- Ollama (optional, for LLM analysis)\n\n## Installation\n\n### Prerequisites\n\n1. **Install Python 3.10**: Make sure you have Python 3.10 installed (not 3.11+)\n2. **Install Ollama** (optional): For LLM analysis features\n\n   ```bash\n   # macOS\n   brew install ollama\n\n   # Or download from https://ollama.ai\n   ```\n\n### Quick Start\n\n1. **Clone the repository**:\n\n   ```bash\n   git clone https://github.com/namuan/meeting-buddy.git\n   cd meeting-buddy\n   ```\n\n2. **Install dependencies**:\n\n   ```bash\n   make install\n   ```\n\n3. **Run the application**:\n   ```bash\n   make run\n   ```\n\n## Usage\n\n### Basic Usage\n\n1. **Launch the application**:\n\n   ```bash\n   make run\n   ```\n\n2. **Select Audio Input**: Choose your preferred audio input device from the dropdown\n\n3. **Start Recording**: Click the \"Start Recording\" button to begin capturing audio\n\n4. **View Transcription**: Watch as your speech is transcribed in real-time\n\n5. **AI Analysis** (optional): If you have Ollama running, enter a prompt to analyze the transcription\n\n6. **Stop Recording**: Click \"Stop Recording\" when finished\n\n### Audio Setup (macOS)\n\nInstall BlackHole (via brew)\n\n```shell\nbrew install blackhole-2ch\n```\n\nFor optimal audio capture on macOS:\n\n1. Open **Audio MIDI Setup** (Applications \u003e Utilities)\n2. Configure your audio devices as shown:\n\n![Audio MIDI Setup](assets/audio-midi-setup.png)\n\n\u003e [!WARNING]\n\u003e If you can't see BlackHole in the list, you may need to `sudo killall coreaudiod`\n\n3. Set the correct sound output device:\n\n![Sound Output Device](assets/sound-output-device.png)\n\n## Configuration\n\n### LLM Integration\n\nTo use LLM analysis features:\n\n1. **Install Ollama**: Follow the installation instructions above\n2. **Start Ollama**:\n   ```bash\n   ollama serve\n   ```\n3. **Pull a model** (e.g., llama3.2):\n   ```bash\n   ollama pull llama3.2\n   ```\n4. **Configure in app**: The application will automatically detect running Ollama instances\n\n## Troubleshooting\n\n### Common Issues\n\n1. **No audio devices detected**:\n\n   - Check that your microphone is connected and recognized by the system\n   - Try running with verbose logging: `make run -v`\n\n2. **Transcription not working**:\n\n   - Ensure OpenAI Whisper is properly installed\n   - Check audio input levels\n   - Verify the selected audio device is working\n\n3. **LLM analysis not available**:\n\n   - Make sure Ollama is installed and running\n   - Verify you have pulled at least one model\n   - Check Ollama is accessible at the default port (11434)\n\n4. **Application won't start**:\n   - Ensure you're using Python 3.10 (not 3.11+)\n   - Try reinstalling dependencies: `make install`\n   - Check the logs for specific error messages\n\n### Logging\n\nFor debugging issues, run with increased verbosity:\n\n```bash\nuv run meeting-buddy -vv\n```\n\nLogs will help identify issues with audio devices, transcription, or LLM connectivity.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnamuan%2Fmeeting-buddy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnamuan%2Fmeeting-buddy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnamuan%2Fmeeting-buddy/lists"}