{"id":22761630,"url":"https://github.com/spences10/audiomind","last_synced_at":"2026-04-30T10:39:03.926Z","repository":{"id":267427524,"uuid":"900256242","full_name":"spences10/audiomind","owner":"spences10","description":"An MP3 to AI Chat Assistant - A configurable AI chat assistant that can be customized for your content and use case. Transform audio content into interactive, searchable conversations.","archived":false,"fork":false,"pushed_at":"2025-03-25T19:47:45.000Z","size":371,"stargazers_count":0,"open_issues_count":12,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T20:38:45.460Z","etag":null,"topics":["deepgram","libsql","svelte","svelte5","sveltekit","turso","voyageai"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","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/spences10.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}},"created_at":"2024-12-08T09:55:54.000Z","updated_at":"2025-03-16T06:55:02.000Z","dependencies_parsed_at":"2024-12-10T09:39:03.973Z","dependency_job_id":"5fd7e068-7f23-4a64-bfd8-ba6d6f3dd118","html_url":"https://github.com/spences10/audiomind","commit_stats":null,"previous_names":["spences10/audiomind"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Faudiomind","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Faudiomind/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Faudiomind/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/spences10%2Faudiomind/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/spences10","download_url":"https://codeload.github.com/spences10/audiomind/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246296615,"owners_count":20754635,"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","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":["deepgram","libsql","svelte","svelte5","sveltekit","turso","voyageai"],"created_at":"2024-12-11T09:14:20.413Z","updated_at":"2026-04-30T10:39:03.920Z","avatar_url":"https://github.com/spences10.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AudioMind\n\nA podcast transcription and semantic search tool with an AI-powered\nchat interface. Transcribe audio files, generate embeddings, and ask\nquestions about your podcast content using RAG (Retrieval Augmented\nGeneration).\n\n## Features\n\n- **Audio Transcription** - Transcribe podcasts using Deepgram's Nova-3\n  model with smart formatting and paragraph detection\n- **Semantic Search** - Vector similarity search powered by Voyage AI\n  embeddings and sqlite-vec\n- **AI Chat Interface** - Ask questions about your podcasts with\n  context-aware responses using Claude\n- **ID3 Tag Support** - Automatically extract podcast and episode\n  metadata from audio files\n- **Local Storage** - All data stored locally in SQLite\n\n## Requirements\n\n- Node.js 22+\n- pnpm\n- API keys for:\n  - [Deepgram](https://deepgram.com) - Audio transcription\n  - [Voyage AI](https://voyageai.com) - Text embeddings\n  - [Anthropic](https://anthropic.com) - AI chat (Claude)\n\n## Setup\n\n1. Clone the repository and install dependencies:\n\n```sh\npnpm install\n```\n\n2. Create a `.env` file with your API keys:\n\n```sh\nDEEPGRAM_API_KEY=your_key\nVOYAGE_API_KEY=your_key\nANTHROPIC_API_KEY=your_key\n```\n\n3. Initialize the database:\n\n```sh\npnpm cli init\n```\n\n## CLI Usage\n\nThe CLI provides tools for processing audio files and managing your\npodcast library.\n\n### Process an Audio File\n\nFull pipeline - transcribe, embed, and ingest in one command:\n\n```sh\npnpm cli process path/to/episode.mp3\n```\n\nPodcast name and episode title are auto-detected from ID3 tags. Override\nwith flags:\n\n```sh\npnpm cli process episode.mp3 --podcast \"My Podcast\" --episode \"Episode 1\"\n```\n\n### Search Your Library\n\n```sh\npnpm cli search \"topic you're looking for\"\npnpm cli search \"machine learning\" --limit 20\npnpm cli search \"interviews\" --podcast \"Tech Talk\"\n```\n\n### Other Commands\n\n```sh\npnpm cli list                    # List all podcasts and episodes\npnpm cli inspect audio.mp3       # View audio file metadata\npnpm cli transcribe audio.mp3    # Transcribe only (no embedding)\npnpm cli update --podcast 1 --name \"New Name\"  # Update metadata\n```\n\n## Web Interface\n\nStart the development server:\n\n```sh\npnpm dev\n```\n\nThe web interface provides a chat UI where you can ask questions about\nyour ingested podcasts. Responses include source citations with\ntimestamps.\n\n## Tech Stack\n\n- **Frontend**: SvelteKit, Tailwind CSS, shadcn-svelte\n- **Backend**: SvelteKit API routes, better-sqlite3, sqlite-vec\n- **AI**: Anthropic Claude (chat), Voyage AI (embeddings), Deepgram\n  (transcription)\n- **CLI**: citty, music-metadata\n\n## Project Structure\n\n```\nsrc/\n├── cli/           # CLI tool for processing audio\n├── lib/\n│   ├── components/  # Svelte components\n│   └── server/      # Server-side utilities (database, AI clients)\n└── routes/\n    ├── api/         # API endpoints for chat\n    └── chat/        # Chat interface pages\n```\n\n## Development\n\n```sh\npnpm dev          # Start dev server\npnpm check        # Type check\npnpm lint         # Lint code\npnpm test         # Run tests\npnpm build        # Production build\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fspences10%2Faudiomind","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fspences10%2Faudiomind","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fspences10%2Faudiomind/lists"}