Command-line tool
zackees / transcribe-anything
Multi-backend whisper app. Blazing fast. Mac-arm optimized. Easy install. Input a local file or url and this service will transcribe it using Whisper AI. Completely private and Free π€―π€―π€―
This connects Repowise to zackees/transcribe-anything's code. It does not install transcribe-anything.
Repowise maps public repos from their source. Not affiliated with zackees. What is Repowise?
What is transcribe-anything?
transcribe-anything is a command-line tool for transcribing a local media file or a YouTube or Rumble URL. It runs Whisper AI on the input and writes subtitle files and raw text. The project is written in Python and installs from PyPI with pip. To install it, run pip install transcribe-anything and follow the steps below. Its code health is 7.1 out of 10 (Good), ranked #140 of 4,000+ indexed repos. The last commit to transcribe-anything was on Jun 9, 2026.
As of commit 7d18bca, indexed Jun 19, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.
For agentstranscribe-anything.md
Repo facts: type, license, health, rank, contributors
| Type | Command-line tool |
|---|---|
| License | MIT |
| Code health | 7.1 / 10 (Good) |
| Health rank | #140 of 4,000+ indexed repos |
| Last commit | Jun 9, 2026 |
| Bus factor | 1 |
| Size | 111 files, 12,210 lines |
Install transcribe-anything
Commands copied from the README
- 1Install transcribe-anything from PyPI with pip.
pip install transcribe-anything - 2Transcribe a local video file with the default CPU mode.
transcribe-anything video.mp4
Releases on GitHub (latest v4.1.2, Sep 24, 2026)
Explore transcribe-anything
- DocumentationModule-by-module documentation, written from the source.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score and the findings behind it.
- CommitsEach commit's effect on code health.
- OverviewEverything else the index found: contributors, decisions, what changed this week.
Ask about this code in your agent
This connects Repowise to transcribe-anything's code. It does not install transcribe-anything. To install transcribe-anything, use the install steps.
Useful if you want to change or fork transcribe-anything: your agent can ask how it is put together and get answers that cite its files.
Ask about transcribe-anything
Answers come from transcribe-anything's README and source, with the files they cite. Two free answers a day without an account.
Want this for your own codebase? Map your repo free
About this page
Get a page like this for your own codebase
Repowise built this map of zackees/transcribe-anything from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.
Free for 2 public repos, with a page like this one. No card. See how Repowise works
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub
zackees/transcribe-anything FAQ
What is transcribe-anything?
transcribe-anything is a command-line tool that transcribes a local media file or a YouTube or Rumble URL using Whisper AI. It writes subtitle files and raw text from the audio.
How does transcribe-anything work?
transcribe-anything runs the selected Whisper backend inside its own isolated environment. The backend is chosen with the --device option, such as insane, insane-flash, whisperx or mlx.
How do I install transcribe-anything?
transcribe-anything installs with pip install transcribe-anything. After installation, the transcribe-anything command is available in the terminal. See the install steps
What language is transcribe-anything written in?
transcribe-anything is written in Python. The repository also includes shell scripts and a Dockerfile.
How is the transcribe-anything code organized?
The main package is src/transcribe_anything, and its entry point is src/transcribe_anything/__main__.py. Tests are in the tests directory, and ARCHITECTURE.md describes the design.
When should I use transcribe-anything?
transcribe-anything suits transcribing local files or URLs with Whisper AI without uploading the data to a service. It can use GPU acceleration on Windows and Linux and Apple Silicon on Mac.
What license does transcribe-anything use?
transcribe-anything uses the MIT license, identified as MIT in its metadata.
Code health
Hotspots average 5.0, the place fixes pay off most.
On the leaderboards:#37 of 71 Python repos
Key features of transcribe-anything
- Transcribes a local file or a YouTube or Rumble URL with Whisper AI into subtitle files and raw text.
- Selects among several backends with the --device option, including insane, insane-flash, whisperx and mlx.
- Writes a speaker.json file that assigns transcribed text to speakers when a diarization-capable backend is used.
- Runs each Whisper backend in an isolated environment.
- Adds word-level timestamps with the --align option on the insane backends.
- Processes input locally and does not upload it to any service.
How zackees/transcribe-anything works
The transcribe-anything command starts at src/transcribe_anything/__main__.py, which is the package's single entry point. Each Whisper backend runs inside its own isolated environment, so its dependencies do not conflict with the main install. The insane backend is implemented in src/transcribe_anything/insanely_fast_whisper.py, which handles the insanely-fast-whisper model path used by --device insane and --device insane-flash. src/transcribe_anything/server_app.py is a FastAPI application, and src/transcribe_anything/client.py is a central client file in the same package. ARCHITECTURE.md describes the design in more detail.
The codebase has 111 files and 800 symbols in 3 modules, led by Python, Shell and Dockerfile. Code health is 7.1 out of 10, rated good.
Maintain zackees/transcribe-anything?
Claim this page, add a badge to the README, or re-index it.
Claim this page
Sign in with GitHub and we check that you are an admin or maintainer of zackees/transcribe-anything. Then add a badge to the README that links readers here.
Add a badge to your README
Readers click through to this page and can ask transcribe-anything's code a question. A badge also re-indexes the repo every week and marks you as the verified maintainer.
[](https://repowise.dev/repo/zackees/transcribe-anything?src=badge_ask)Paste it at the top of README.md, under the title.
Added it already? Verify to get the mark now instead of tomorrow.
Need HTML or the larger health card? More formatsHide more formats
This badge as HTML
<a href="https://repowise.dev/repo/zackees/transcribe-anything?src=badge_ask"><img src="https://api.repowise.dev/badge/wiki/zackees/transcribe-anything.svg?label=ask" alt="repowise: Ask this codebase"></a>Code health card
The score, its change since the last index, and when it was measured. Follows the reader's light or dark theme.
<a href="https://repowise.dev/repo/zackees/transcribe-anything?src=badge_card"><picture><source media="(prefers-color-scheme: light)" srcset="https://api.repowise.dev/badge/health/zackees/transcribe-anything.svg?style=card&theme=light"><img src="https://api.repowise.dev/badge/health/zackees/transcribe-anything.svg?style=card" alt="repowise code health" width="500" height="168"></picture></a>