{"id":28181141,"url":"https://github.com/manorajesh/pose_to_audio","last_synced_at":"2025-10-04T19:36:56.256Z","repository":{"id":287639286,"uuid":"898368484","full_name":"manorajesh/pose_to_audio","owner":"manorajesh","description":"translate hand poses to music with modular synthesizers","archived":false,"fork":false,"pushed_at":"2025-04-13T01:20:18.000Z","size":29434,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-16T03:12:16.237Z","etag":null,"topics":["handtracking","modular-synthesizers"],"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/manorajesh.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":"2024-12-04T09:16:55.000Z","updated_at":"2025-05-05T08:38:13.000Z","dependencies_parsed_at":"2025-04-13T02:32:06.427Z","dependency_job_id":null,"html_url":"https://github.com/manorajesh/pose_to_audio","commit_stats":null,"previous_names":["manorajesh/pose_to_audio"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/manorajesh/pose_to_audio","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manorajesh%2Fpose_to_audio","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manorajesh%2Fpose_to_audio/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manorajesh%2Fpose_to_audio/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manorajesh%2Fpose_to_audio/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/manorajesh","download_url":"https://codeload.github.com/manorajesh/pose_to_audio/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manorajesh%2Fpose_to_audio/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278366598,"owners_count":25975091,"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":"2025-10-04T02:00:05.491Z","response_time":63,"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":["handtracking","modular-synthesizers"],"created_at":"2025-05-16T03:12:15.951Z","updated_at":"2025-10-04T19:36:56.250Z","avatar_url":"https://github.com/manorajesh.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pose to video\n\nThis small Python project translates hand gestures, including American Sign Language (ASL), into musical expressions through a digital modular synthesizer. By tracking your hand movements in real-time, the script converts spatial positioning, finger movements, and hand gestures into Open Sound Control (OSC) messages that can control various synthesizer parameters.\n\n## Features\n\n- Real-time hand tracking using MediaPipe and OpenCV\n- Tracks multiple hand features simultaneously:\n  - Finger curl detection\n  - Hand velocity measurement\n  - Distance between hands\n  - Vertical positioning\n- OSC protocol integration for seamless connection to digital audio workstations and modular synthesizers\n- Works with both webcam input and video files\n- Supports tracking of both hands simultaneously\n\n## Requirements\n\n- Python 3.6+\n- OpenCV\n- MediaPipe\n- python-osc\n- A compatible OSC receiver (VCV Rack, Max/MSP, Pure Data, etc.)\n\n## Installation\n\n1. Clone this repository:\n\n   ```bash\n   git clone https://github.com/manorajesh/pose_vcv_plugin.git\n   cd pose_to_audio\n   ```\n\n2. Create and activate a virtual environment (optional but recommended):\n\n   ```bash\n   python -m venv env\n   source env/bin/activate  # On Windows, use: env\\Scripts\\activate\n   ```\n\n3. Install the required dependencies:\n   ```bash\n   pip install opencv-python mediapipe python-osc\n   ```\n\n## Usage\n\n### Basic Usage\n\nRun the application with your webcam:\n\n```bash\npython src/main.py\n```\n\n### Using a Video File\n\nYou can also use a pre-recorded video:\n\n```bash\npython src/main.py path/to/your/video.mp4\n```\n\n### OSC Parameters\n\nThe application sends OSC messages to `127.0.0.1:7001` with the following channels:\n\n- `/ch/1`: Finger curl intensity (average curl of all fingers)\n- `/ch/2`: Hand movement velocity\n- `/ch/3`: Distance between hands (when both hands are visible)\n- `/ch/4`: Vertical position of hands\n\n## How It Works\n\n1. **Hand Detection and Tracking**: Using MediaPipe's hand tracking solution, the application identifies hand landmarks in each video frame.\n\n2. **Feature Extraction**: The system extracts key features from the hand tracking data:\n\n   - Finger curl calculation based on joint angles\n   - Movement velocity through frame-to-frame position changes\n   - Inter-hand distance measurement\n   - Spatial positioning of hands\n\n3. **Data Processing**: Raw tracking data is smoothed to remove jitter and improve responsiveness.\n\n4. **OSC Transmission**: Processed data is converted to normalized values and transmitted as OSC messages.\n\n5. **Audio Generation**: When connected to a compatible synthesizer (like VCV Rack), these OSC messages control various sound parameters to create dynamic, gesture-responsive audio.\n\n## American Sign Language Integration\n\nWhile PoseInfo tracks general hand movements, it can respond uniquely to ASL gestures:\n\n- Different finger configurations in ASL signs create distinctive curl patterns\n- The spatial arrangement of ASL signs (location, movement, orientation) generates varied OSC outputs\n- Speed and intensity of signing directly affects the velocity parameters\n\nThis creates an expressive system where ASL can be \"performed\" as a musical instrument, with each sign and movement contributing to the sonic landscape.\n\n## Connecting to Synthesizers\n\n1. Ensure your synthesizer or DAW can receive OSC messages on port 7001 (configurable in the code)\n2. Map the incoming OSC channels to desired parameters:\n   - Map finger curl data to filter cutoffs for gesture-controlled filtering\n   - Use velocity data to control note velocity or LFO rates\n   - Map hand distance to effects like reverb depth or delay feedback\n   - Use vertical positioning to control pitch or modulation intensity\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanorajesh%2Fpose_to_audio","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanorajesh%2Fpose_to_audio","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanorajesh%2Fpose_to_audio/lists"}