Speakr

Speakr is a self-hosted AI transcription and note-taking platform for individuals and privacy-conscious groups that turns audio recordings into searchable,…

  • AI
  • Media Applications
  • Productivity
  • Tools & Utilities
Speakr is a self-hosted AI transcription and note-taking platform for individuals and privacy-conscious groups that turns audio recordings into searchable, shareable notes with speaker identification, AI chat, and retention controls.

Platform availability

Available on 2 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

67/100 Good

Maintained
100last commit 19 days ago
Popular
724,148 GitHub stars
Easy to install
452 install platforms, install notes, Docker image
Light to run
602 GB minimum RAM, runs on ARM
Security check
201 serious finding, 2 minor, CI, tests

Availability: platform listings confirmed today, links checked 45 days ago

GitHub stars
4,148
Open issues
12
Last commit
2026-11-02
Latest release
v0.10.18-alpha
License
AGPL-3.0
Activity
rising

Checked 19 days ago - source: GitHub (murtaza-nasir/speakr)

Resources & Compatibility

Minimum requirements: 2 GB RAM, 2 CPU core(s), 20 GB disk. ARM (e.g. Raspberry Pi) is supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Grab the starter config file Before starting anything, download the official example docker-compose.yml file (Docker's recipe for running the app). If you skip this, Docker won't know which pieces to start or where the speech-to-text service should be. source
  • Start services on the right machines On the speech-to-text (ASR) machine, start its compose file first, then start the main Speakr compose file on your Speakr machine. Starting the wrong file, or not starting both, can leave the app unable to turn audio into text. source
  • Fill in model API settings In your config, set the website address (base URL), password (API key), and model name for background summaries and chat. If these AI service details are missing or wrong, those features will fail even though the app may load. source
  • API access Provide API keys for OpenAI, OpenRouter, or local AI services for transcription and text generation. source

Fetched 38 days ago - each note links to its source

Alternatives (8)

  • FUTO Voice Input - FUTO Voice Input is an application that lets you do speech-to-text on Android, integrating with third party keyboards or apps that use the…
  • FluidVoice
  • MacWhisper - Quickly and easily transcribe audio files into text with OpenAI's state-of-the-art transcription technology Whisper.
  • Otter.ai - An AI-powered tool that transcribes voice conversations in real-time, ideal for professionals, journalists, and students for meetings, inte…
  • Spokenly - Real-time voice dictation for Mac with instant transcription, customizable shortcuts, advanced voice recognition, no data collection, and b…
  • Vibe Transcribe - Provides fully offline audio and video transcription with local AI models, batch processing, real-time preview, multi-format export, transl…
  • VoiceInk - Transcribes speech instantly with local AI for near-perfect accuracy and privacy, featuring real-time native macOS support and user-provide…
  • Whisper - Whisper provides a simple way to share secret information with someone else, such as passwords, credentials, keys, or other sensitive data.

Checked 51 days ago - source: AlternativeTo

Common questions

Do I need separate compose files for the speech-to-text service and Speakr?

Yes. Start the ASR compose file on the speech-to-text machine first, then start the main Speakr compose file on the Speakr machine. Starting the wrong file or not starting both can prevent transcription.

What must be set in the config for background summaries and AI chat?

Set the base URL, API key or password, and model name for the AI service. If those details are missing or wrong, those features can fail even if Speakr loads.

Can I limit LLM and transcription usage per user?

Yes. Speakr supports usage budgets for LLM tokens and transcription minutes, per user.

Can I use Speakr from a phone?

Speakr is an installable Progressive Web App that is mobile-first and offline-capable. It also includes a phone share-target.

What should I check first if Speakr has an issue?

Most problems fall into installation issues, transcription failures, performance problems, or feature-specific quirks. The troubleshooting guide is meant to help identify and resolve common issues.

Answers sourced from github.com, github.com, github.com, murtaza-nasir.github.io

Community

Collected 53 days ago - public community threads