# Speakr

> Self-hosted AI transcription and intelligent note-taking platform

- Canonical URL: https://www.fosshunter.com/tools/speakr
- JSON export: https://www.fosshunter.com/tools/speakr.json
- Website: https://github.com/murtaza-nasir/speakr
- Category: Voice
- Open source: yes
- Self-hostable: yes
- Verified listing: no
- Featured: no
- Published at: 2026-11-03T05:47:33+00:00
- Catalog revision: `903966813`

## Repository metrics (point-in-time)

- Repository: https://github.com/murtaza-nasir/speakr
- Stars: 4154
- Forks: 352
- Open issues: 9
- License: AGPL-3.0
- Last push: 2026-11-03T06:09:58+00:00
- Metrics observed at (synced_at): 2026-11-04T06:59:52+00:00
- Archived: no

Tags: Voice, Transcription, AI Transcription, Diarization
Tech stacks: CSS, docker, HTML, javascript, nodejs, python, WhisperX

## Features
- Supports flexible recording from microphones, system audio, or drag and drop files. *(highlighted)*
- Features automatic speaker diarization to label who said what in recordings. *(highlighted)*
- Integrates with multiple AI engines like WhisperX and OpenAI for processing. *(highlighted)*

## Description

Speakr is a self-hosted AI transcription and note-taking platform that transforms audio into organized, searchable knowledge. It features flexible input options, long session support, and automatic speaker diarization for maximum privacy.

---
Source: [FOSSHunter — Speakr](https://www.fosshunter.com/tools/speakr) — cite `synced_at` and the catalog revision when quoting metrics.
Interpretation rules: https://www.fosshunter.com/llms-full.txt