babelscribe
Offline tool that turns audio/video into SRT/VTT subtitles and text in 99 languages using local GPU.
Tested on macOS and Linux
Use it
macOS arm64
You need first
- Runtimes:
Python 3.9+ - A GPU is optional
install babelscribe via uv tool install
uv tool install babelscribe
Check that it works
babelscribe --helpThe output should contain “babelscribe — transcribe any audio/video”.
Run babelscribe models to see the available speech models.
Linux x86_64
You need first
- Runtimes:
Python 3.9+ - A GPU is optional
Install babelscribe via uv tool
uv tool install babelscribe
Where the README and reality differ
- README: --translate writes the transcript translated to English
What worked: installed babelscribe 0.3.2 CLI has no --translate option (error: unrecognized arguments)
Check that it works
babelscribe --version 2>&1The output should contain “0.3.2”.
First thing to try
babelscribe models 2>&1Run babelscribe models to see the available speech models.
What it does
- Turn audio or video into subtitlesTested
How to use it
- Run
babelscribe <file> -l en -m tiny --flavor cpu -f srt,txtto transcribe a file. - Open the .srt and .txt files written next to the input file.
- Run
- Transcribe files from AI apps via MCPNot shown working
- Translate transcripts to EnglishNot tested
How far pickfit got
macOS arm64
- Installs
- Starts
- 0 of 3 features work
- Works offline
Linux x86_64
- Installs
- Starts
- 1 of 3 features work
- Works offline
Other systems
Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- make SRT subtitles from a video offline
- translate transcription to English subtitles
- transcribe Thai video with accurate hybrid model
An alternative to whisper.cpp, faster-whisper and WhisperX.
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
macOS arm64
Installs and starts
- Replayed from scratch
- Works offline
- Checked on 1 Nov 2026
- Version 0.3.2
Differences the test machine hit
- README: pip install babelscribe
In the test: use uv tool install babelscribe to avoid PEP 668 isolated install - README: babelscribe devices / models lists GPUs and models
In the test: first run triggers download of whisper-cli and large-v3-turbo model (1.6GB); timed out after 30s - README: babelscribe interview.mp4 auto-picks large-v3-turbo
In the test: tested with -m tiny (75 MB) to avoid large download; transcription of silence.wav succeeded
Linux x86_64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 0.3.2
Differences the test machine hit
- README: auto-detects GPU backend (Vulkan on Linux) with no extra flags
In the test: removed cached Vulkan build and retried with --flavor cpu -m tiny; CPU build ran and transcribed