murtaza-nasir/speakr

Speakr is a personal, self-hosted web application designed for transcribing audio recordings

What it solves

Speakr provides a private, self-hosted platform for transcribing audio and video recordings into organized, searchable notes. It addresses the need for privacy-conscious users to manage large volumes of meeting or lecture recordings without relying on third-party cloud storage or SaaS platforms.

How it works

Speakr acts as a central hub that connects to your preferred transcription engine (such as WhisperX, OpenAI, or various self-hosted ASR services). Once audio is captured or uploaded, the platform automatically transcribes it, identifies speakers (diarization), and generates summaries or extracts action items using configurable AI prompts. Users can interact with their library through a chat interface that cites specific timestamps in the original audio, or use an agentic mode to perform complex research across multiple recordings.

Who it’s for

It is designed for individuals, research teams, or organizations that require secure, long-term storage of audio data and need to automate the process of turning spoken content into actionable knowledge, such as meeting minutes, research notes, or study guides.

Highlights

  • Flexible Transcription: Supports multiple backends including WhisperX, OpenAI, and self-hosted options like VibeVoice or OpenASR.
  • Agentic Research: Features an opt-in AI researcher that can search and synthesize information across your entire library of recordings.
  • Privacy-First: Runs entirely on your own infrastructure with support for SSO and granular access controls.
  • Customizable Workflows: Uses "smart tags" that allow you to apply specific AI prompts and transcription settings to different types of recordings automatically.
  • Extensible: Includes a REST API and webhook support for integrating with tools like Obsidian, n8n, or Zapier.

Related

  • Project
    rishikanthc/Scriberr

    An open-source, offline audio transcription app for self-hosters that provides private, local transcription, speaker diarization, and AI-powered chat with transcripts.

  • Project
    OpenWhispr/openwhispr

    A privacy-first, open-source voice-to-text application providing local AI dictation, meeting transcription with speaker diarization, and AI-powered notes.

  • Project
    Notely-Voice/NotelyVoice

    A private, cross-platform AI voice transcription and note-taking app that uses OpenAI Whisper to provide offline speech-to-text capabilities.

  • Project
    ideaplexa/voicetypr

    Voicetypr is an open‑source, offline‑first dictation app for macOS and Windows. It captures speech via a global hot‑key, transcribes locally with Whisper (and Parakeet on Apple Silicon) or optionally via cloud STT services, can clean up the text with LLMs, and inserts the result at the current cursor. A companion CLI lets scripts or AI agents use the same transcription pipeline, returning plain text or JSON. The app is built with Tauri (Rust backend) and React, offers LAN‑based private transcription servers, and is released under AGPL‑3.0.

  • Project
    harry0703/AudioNotes

    A local-first audio and video transcription tool that converts recordings into structured Markdown notes and enables AI-powered Q&A over the content.