{"id":31640003,"url":"https://github.com/jonaylor89/freqmoda","last_synced_at":"2025-10-07T02:09:00.831Z","repository":{"id":306798814,"uuid":"936980427","full_name":"jonaylor89/freqmoda","owner":"jonaylor89","description":"audio editing server and playground","archived":false,"fork":false,"pushed_at":"2025-08-12T02:57:57.000Z","size":94128,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-16T13:17:47.576Z","etag":null,"topics":["audio-processing","axum","mcp","rust","streaming"],"latest_commit_sha":null,"homepage":"https://blog.jonaylor.com/building-a-simple-ai-daw-part-2-mcp-and-agents","language":"Rust","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/jonaylor89.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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},"funding":{"github":["jonaylor89"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"thanks_dev":null,"custom":null}},"created_at":"2025-02-22T03:52:12.000Z","updated_at":"2025-08-19T13:41:20.000Z","dependencies_parsed_at":"2025-07-27T18:56:13.777Z","dependency_job_id":null,"html_url":"https://github.com/jonaylor89/freqmoda","commit_stats":null,"previous_names":["jonaylor89/freqmoda"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jonaylor89/freqmoda","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonaylor89%2Ffreqmoda","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonaylor89%2Ffreqmoda/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonaylor89%2Ffreqmoda/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonaylor89%2Ffreqmoda/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jonaylor89","download_url":"https://codeload.github.com/jonaylor89/freqmoda/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonaylor89%2Ffreqmoda/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278708004,"owners_count":26031932,"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":"2025-10-07T02:00:06.786Z","response_time":59,"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":["audio-processing","axum","mcp","rust","streaming"],"created_at":"2025-10-07T02:08:40.728Z","updated_at":"2025-10-07T02:09:00.823Z","avatar_url":"https://github.com/jonaylor89.png","language":"Rust","funding_links":["https://github.com/sponsors/jonaylor89"],"categories":[],"sub_categories":[],"readme":"\n# FreqModa\n\nAI-powered audio processing chat application that lets users manipulate audio files through natural language conversations.\n\n## Architecture\n\nFreqModa consists of several integrated services:\n\n- **Streaming Engine**: Core audio processing server (Rust)\n- **Gateway Service**: AI chat orchestrator with Claude integration (Rust)\n- **MCP Server**: Model Context Protocol integration for direct LLM access (Node.js)\n\n## Quick Start\n\n### Prerequisites\n\n- Rust 1.70+\n- Docker\n- Claude API key from Anthropic\n\n## Services\n\n### Streaming Engine (`streaming-engine/`)\n\nAdvanced audio processing server that handles real-time audio manipulation.\n\n- **Port**: 8080\n- **Features**: Format conversion, effects, filters, time manipulation\n- **API**: RESTful with streaming support\n- **Storage**: Local, S3, GCS support\n\n[📖 Full Documentation](./streaming-engine/README.md)\n\n### Gateway Service (`gateway-service/`)\n\nRust-based API gateway that orchestrates communication between Claude AI and the streaming engine.\n\n- **Port**: 9000\n- **Features**: Natural language processing, conversation management, audio processing orchestration\n- **Database**: PostgreSQL for conversation history\n- **AI**: Claude 3.5 Sonnet integration\n\n[📖 Full Documentation](./gateway-service/README.md)\n\n### Web Interface\n\nThe gateway service includes a built-in web interface available at http://localhost:9000:\n\n- **Features**: Chat interface, audio playback, sample library\n- **Demo Mode**: Rate-limited for demonstration purposes\n- **Responsive**: Works on desktop and mobile devices\n\n## API Examples\n\n### Chat with AI for Audio Processing\n\n```bash\ncurl -X POST http://localhost:9000/api/chat \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"message\": \"Reverse Sample 1 and add a medium echo effect\"\n  }'\n```\n\n### Direct Audio Processing\n\n```bash\ncurl -X POST http://localhost:9000/api/audio/process \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"audio_name\": \"sample1.mp3\",\n    \"parameters\": {\n      \"reverse\": true,\n      \"echo\": \"medium\",\n      \"fade_in\": 1.0\n    }\n  }'\n```\n\n### Streaming Engine Direct Access\n\n```bash\n# Process audio with effects\ncurl \"http://localhost:8080/unsafe/sample1.mp3?reverse=true\u0026echo=0.8:0.88:60:0.4\u0026fade_in=1\"\n\n# Get audio metadata\ncurl \"http://localhost:8080/meta/unsafe/sample1.mp3\"\n```\n\n## Audio Sample Library\n\nThe system includes a pre-loaded library of 10 high-quality audio samples:\n\n- **Sample 1**\n- **Sample 2** \n- **Sample 3**\n- **Sample 4** \n- **Sample 5**\n- **Sample 6** \n- **Sample 7** \n- **Sample 8** \n- **Sample 9**\n- **Sample 10**\n\n## Development\n\n### Project Structure\n\n```\nfreqmoda/\n├── streaming-engine/          # Core audio processing server\n│   └── mcp-server/           # MCP integration for direct LLM access\n├── gateway-service/           # AI chat orchestrator  \n├── mcp-server/               # Shared MCP artifacts\n├── scripts/                  # Development utilities\n├── docs/                     # Project documentation\n└── migrations/               # Database schema migrations\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonaylor89%2Ffreqmoda","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjonaylor89%2Ffreqmoda","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonaylor89%2Ffreqmoda/lists"}