Scriberr

Scriberr is an open-source, self-hosted audio transcription and summarization tool that runs OpenAI Whisper models locally to convert audio files into…

  • AI
  • Media Applications
  • Other
  • Productivity
  • Tools & Utilities
Scriberr is an open-source, self-hosted audio transcription and summarization tool that runs OpenAI Whisper models locally to convert audio files into private, offline text.

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.

56/100 Fair

Maintained
69last commit 62 days ago
Popular
703,159 GitHub stars
Easy to install
452 install platforms, install notes, Docker image
Light to run
1010 GB minimum RAM

Availability: platform listings confirmed today, links checked 18 days ago

GitHub stars
3,159
Open issues
126
Last commit
2026-09-20
Latest release
v1.2.0
License
MIT
Activity
stale

Checked today - source: GitHub (rishikanthc/Scriberr)

Resources & Compatibility

Minimum requirements: 10 GB RAM, 40 GB disk.

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

First-install notes

  • Docker deployment Scriberr runs as a self-contained Docker deployment bundling a Go backend, embedded web frontend, and a Python-based ML runtime for the speech models. source

Fetched 48 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…
  • MacWhisper - Quickly and easily transcribe audio files into text with OpenAI's state-of-the-art transcription technology Whisper.
  • Paraspeech - Offline speech-to-text tool for macOS focused on privacy, optimized for Apple Silicon, lightweight with less than 200MB RAM, no subscriptio…
  • Scrib - On-device voice transcription.
  • 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 54 days ago - source: AlternativeTo

Common questions

What does the Docker deployment include?

The Docker deployment is self-contained and bundles a Go backend, embedded web frontend, and Python-based ML runtime for the speech models.

Does Scriberr keep transcription offline?

Yes, it is completely offline and self-hosted, running entirely on your own machine.

Which speech recognition stack does it use?

It uses OpenAI's open-source Whisper models with the WhisperX transcription engine on your local hardware.

Does it support speaker labels and summaries?

Yes, it can provide transcript text, speaker labels, and AI summaries without sending data to the cloud.

Answers sourced from deepwiki.com, github.com, scriberr.app, spineye.com

Community

Collected 48 days ago - public community threads