Scriberr
A self-hosted, offline audio transcription app that runs AI speech recognition on your own hardware.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About Scriberr
Scriberr is an open-source audio transcription application for self-hosters who want to keep recordings off third-party services. You run it on your own server, upload audio and get transcripts back through a web interface, with an API documented for integrations. Transcription runs completely offline.
It ships as Docker images, including CUDA builds for NVIDIA GPUs. The developer paused work for a period and has posted in the README that development is resuming.
Strengths
- Transcription runs fully offline on your own hardware
- Docker images, including CUDA builds for GPU acceleration
- Web interface plus a documented API
Limitations
- Requires running your own server
- Development was paused for a time and is only now resuming
Details
- Pricing
- FreeFree and open source under the MIT licence.
- License
- MIT
- Developer
- rishikanthc
- Platforms
- Web, Self-hosted
- How it runs
- Self-hosted
- Works offline
- Yes
- Best suited for
- Self-hosters who want private transcription of recordings and interviews
- Categories
- Local AI tools, AI voice, AI meeting notes
- Last verified
- Added
Alternatives to Scriberr
Compare allSoftware that can replace Scriberr for an important use case, and what changes if you switch.
Whishper
A self-hosted web app for transcribing, translating and editing subtitles locally with Whisper models.
Whishper is an AGPL-3.0 self-hosted Whisper app with a subtitle editor and LibreTranslate translation, but it has no user authentication and awaits a rewrite.
Whisper-WebUI
A browser interface for generating subtitles and transcripts locally with Whisper speech recognition models.
Whisper-WebUI is an Apache-2.0 browser interface offering three Whisper implementations, subtitle exports and diarization, which requires a Hugging Face token and accepted model terms.
noScribe
Transcribes recorded audio to text on your own computer, with speaker separation.
noScribe is a GPL-3.0 desktop app for Windows, macOS and Linux that transcribes with speaker separation locally, with no server to run.
Vibe
Transcribe audio and video files on your own computer.
Vibe is an MIT desktop app that transcribes files locally with batch jobs and several subtitle formats, avoiding the need to host your own server.
Buzz
Turn speech recordings into text with a desktop transcription app.
Buzz is an MIT desktop transcription app for Windows, macOS and Linux that adds microphone transcription and subtitle exports without a self-hosted server.
aTrain
Transcribe recorded interviews on your own computer.
aTrain is an AGPL-3.0 desktop tool for Windows and Linux that transcribes interviews locally with speaker detection, installed on one computer rather than served.
WhisperX
A speech recognition tool that adds word-level timestamps and speaker diarization to Whisper transcription.
WhisperX runs locally from the command line with word-level timestamps and speaker diarization, but it has no graphical interface and its license is not stated.
MacWhisper
A Mac app that transcribes audio and video files to text on your own machine.
MacWhisper is a closed-source freemium Mac app with local Whisper, Qwen and Parakeet models and speaker recognition, limited to macOS rather than a web server.
Scriberr as an alternative
Listings that name Scriberr as an alternative.
Rev
An AI and human transcription service with captioning, a transcript editor and a mobile voice recorder app.
Scriberr is a free MIT self-hosted app that transcribes offline on your own server with a web interface and API, instead of sending audio to Rev.
Sonix
An online transcription service that converts audio and video to text in over 54 languages.
Scriberr is free MIT software that transcribes fully offline on your own server with a web interface and API, but you must run and maintain that server.
Trint
A web platform that transcribes audio and video to editable, searchable text with AI summaries.
Scriberr is a free MIT self-hosted app that transcribes offline on your own hardware with a web interface and API, which you must host yourself.
Whisper
An open-source speech recognition model from OpenAI for transcribing and translating audio on your own machine.
Scriberr turns local transcription into a self-hosted web app with an API and CUDA Docker images, which means running and maintaining your own server.
whisper.cpp
C/C++ port of OpenAI's Whisper for fast offline speech-to-text on your own hardware.
Scriberr runs offline transcription as a self-hosted web app with a documented API and CUDA Docker images, which requires running your own server.
Similar software
Related functionality, not necessarily a direct replacement.
Speaches
A self-hosted, OpenAI API-compatible server for local speech-to-text, translation and text-to-speech models.
