{"name":"Speakr: Self-Hosted AI Transcription and Intelligent Note-Taking Platform","description":"Speakr is a powerful, self-hosted web application for transcribing audio recordings into organized, searchable, and intelligent notes. It prioritizes privacy by running on your own infrastructure and offers advanced AI features like speaker identification, interactive chat, and semantic search. This platform is ideal for individuals and groups seeking to transform audio into actionable insights while maintaining full control over their data.","github":"https://github.com/murtaza-nasir/speakr","url":"https://osrepos.com/repo/murtaza-nasir-speakr","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/murtaza-nasir-speakr","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/murtaza-nasir-speakr.md","json":"https://osrepos.com/repo/murtaza-nasir-speakr.json","topics":["Python","AI","Transcription","Self-Hosted","Audio","Note-Taking","Privacy","Web Application"],"keywords":["Python","AI","Transcription","Self-Hosted","Audio","Note-Taking","Privacy","Web Application"],"stars":null,"summary":"Speakr is a powerful, self-hosted web application for transcribing audio recordings into organized, searchable, and intelligent notes. It prioritizes privacy by running on your own infrastructure and offers advanced AI features like speaker identification, interactive chat, and semantic search. This platform is ideal for individuals and groups seeking to transform audio into actionable insights while maintaining full control over their data.","content":"## Introduction\nSpeakr is an innovative, self-hosted web application designed to revolutionize how you manage audio recordings. It transforms raw audio into organized, searchable, and intelligent notes, all while ensuring your privacy by operating entirely on your own infrastructure. Built with Python and Vue.js, Speakr offers a comprehensive suite of features for transcription, collaboration, and smart organization, making it an ideal solution for anyone needing to convert spoken words into actionable text.\n\n## Installation\nGetting Speakr up and running is straightforward, especially using Docker. This method ensures all dependencies are managed efficiently.\n\nFirst, create a project directory and navigate into it:\nbash\nmkdir speakr && cd speakr\n\n\nNext, download the `docker-compose.yml` configuration and the environment template:\nbash\nwget https://raw.githubusercontent.com/murtaza-nasir/speakr/master/config/docker-compose.example.yml -O docker-compose.yml\nwget https://raw.githubusercontent.com/murtaza-nasir/speakr/master/config/env.transcription.example -O .env\n\n\nBefore launching, you'll need to configure your API keys in the `.env` file. Open it with a text editor like `nano`:\nbash\nnano .env\n\nEnsure you set `TRANSCRIPTION_API_KEY` (for OpenAI or similar) or `ASR_BASE_URL` (for self-hosted WhisperX) and `TEXT_MODEL_API_KEY` (for summaries, titles, and chat).\n\nFinally, launch Speakr using Docker Compose:\nbash\ndocker compose up -d\n\nYou can then access Speakr at `http://localhost:8899`. For detailed installation options, including self-hosted WhisperX with GPU support, refer to the official documentation.\n\n## Examples\nSpeakr's versatility shines through its real-world use cases and creative tag prompts, allowing users to tailor its functionality to specific needs.\n\n**Real-World Use Cases:**\n*   **Family Memories:** Create a \"Family\" group with a protected tag to automatically share and preserve recordings of trips and events indefinitely.\n*   **Book Club Discussions:** Use a \"Book Club\" group and tag monthly meetings for automatic sharing among members, allowing for personal notes.\n*   **Work Project Groups:** Share recordings individually with teammates for temporary collaboration, with easy revocation of access when projects conclude.\n*   **Daily Standups:** Implement a group tag with a 14-day retention policy for automatic sharing and cleanup of routine meetings.\n*   **Legal Consultations:** Utilize a group tag with a 7-year retention policy for automatic sharing with a legal group, ensuring compliance-based retention.\n\n**Creative Tag Prompt Examples:**\nSpeakr's smart tagging system allows for custom AI prompts, transforming raw recordings into structured outputs:\n*   **Recipe Recordings:** Tag recordings of yourself cooking with \"Recipe\" to convert spoken instructions into formatted recipes with ingredient lists and numbered steps.\n*   **Lecture Notes:** Students can tag lectures with \"Study Notes\" to generate organized outlines with concepts, examples, and definitions.\n*   **Meeting Summaries:** An \"Action Items\" tag can filter discussions to return only decisions, tasks, and deadlines.\n*   **Tag Stacking:** Combine multiple tags, such as \"Recipe\" + \"Gluten Free\", to get a formatted recipe with gluten substitution suggestions, demonstrating powerful layered AI instructions.\n\n## Why Use Speakr\nSpeakr stands out as a premier solution for audio transcription and intelligent note-taking due to several compelling reasons:\n*   **Privacy-First & Self-Hosted:** It runs entirely on your own infrastructure, ensuring sensitive conversations remain private and under your control.\n*   **Advanced AI Capabilities:** Features high-accuracy AI transcription with speaker identification, voice profiles, interactive chat to query recordings, and semantic search across all your notes.\n*   **Robust Collaboration:** Offers internal sharing with granular permissions, group management with automatic sharing via group-scoped tags, and secure public sharing options.\n*   **Intelligent Organization:** Utilizes smart tagging with custom AI prompts and tag stacking for powerful transformations, alongside flexible retention policies and automatic cleanup.\n*   **Seamless Integrations:** Supports automated exports to popular note-taking systems like Obsidian and Logseq, documentation wikis, and can be integrated into project management workflows via its comprehensive REST API.\n*   **User-Friendly Interface:** Provides a beautiful, internationalized interface with light/dark modes, audio-transcript synchronization, and performance optimizations for large transcripts.\n\n## Links\n*   [GitHub Repository](https://github.com/murtaza-nasir/speakr)\n*   [Official Documentation](https://murtaza-nasir.github.io/speakr)\n*   [Quick Start Guide](https://murtaza-nasir.github.io/speakr/getting-started)\n*   [Docker Hub](https://hub.docker.com/r/learnedmachine/speakr)\n*   [Latest Releases](https://github.com/murtaza-nasir/speakr/releases)","metrics":{"detailViews":7,"githubClicks":3},"dates":{"published":null,"modified":"2026-01-15T20:01:13.000Z"}}