In simple English
This tool turns recordings into written text. You can edit the text and fix any mistakes the computer makes. Multiple people can work on the same file at the same time. You can run it on your own server so your files stay private. It costs nothing to use, but you need some technical skill to set it up.
What it is
Transcribee is a self-hosted web application for transcribing audio and video files with speaker labels. It combines speech recognition models with a collaborative text editor.
What it is good for
Solo builders and small teams who want to transcribe interviews or meetings without sending sensitive audio files to paid cloud services.
- Keeps your audio files and transcripts entirely on your own server.
- Includes speaker identification to separate different voices in the recording.
- Allows multiple people to edit the same transcript at the same time.
- Requires technical knowledge to install and configure for self-hosting.
- Concurrent editing can cause performance problems on larger files.
- Has many open issues as the project is still in early development.
Paid cloud transcription services
Docker
- ggml-org/whisper.cpp55k stars
Runs speech recognition locally on your hardware through the command line.
- mpv-player/mpv38k stars
A command-line media player that handles most audio, video and subtitle formats and can be driven entirely from scripts.
- snapcast/snapcast8.0k stars
A server and clients that play one audio stream in several rooms, kept in time with each other.
- MusicPlayerDaemon/MPD2.8k stars
A background music player with no interface of its own, controlled over a network by separate client programs.
git clone https://github.com/bugbakery/transcribee.git cd transcribee docker compose up