pickfit

BrowseLocal AI tools

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
  1. install babelscribe via uv tool install

    uv tool install babelscribe

Check that it works

babelscribe --help

The 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
  1. 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>&1

The output should contain “0.3.2”.

First thing to try

babelscribe models 2>&1

Run babelscribe models to see the available speech models.

What it does

  • Turn audio or video into subtitles
    How to use it
    1. Run babelscribe <file> -l en -m tiny --flavor cpu -f srt,txt to transcribe a file.
    2. Open the .srt and .txt files written next to the input file.
    Tested
  • Transcribe files from AI apps via MCP
    Not shown working
  • Translate transcripts to English
    Not tested

How far pickfit got

macOS arm64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Linux x86_64

  1. Installs
  2. Starts
  3. 1 of 3 features work
  4. Works offline

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

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.