# 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 🤯🤯🤯

Repository: https://github.com/zackees/transcribe-anything
Canonical: https://ross.abutalabs.com/products/transcribe-anything
Homepage: https://pypi.org/project/transcribe-anything/
Language: Python
License: MIT
License Family: permissive
Topics: cli, diarization, python, speech-to-text, subtitles, transcription, whisper
Last push: 2026-07-11T00:49:47+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 92, longevity 100
- inputs: {"age_days": 1943, "days_push": 54, "days_rel": 54, "gap_med": 1, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1393, forks 140 (observed 2026-08-28T04:04:36.314135+00:00)

## What it is
A Python CLI app that transcribes local audio/video files or URLs (YouTube, Rumble, etc.) using multiple Whisper backends with automatic device routing and isolated per-backend environments. It outputs text, SRT/VTT subtitles, JSON, and speaker-diarized transcripts.

## Use cases
- transcribe a youtube video to text
- generate srt subtitles from an mp4
- convert a lecture recording into a transcript
- get a speaker-diarized transcript of a podcast
- run whisper locally on apple silicon for privacy
- transcribe audio files without installing cuda/torch manually

## When to choose
- you want a one-command transcription tool that works across mac, windows, and linux
- you need multiple whisper backends (openai-whisper, whisperx, mlx, insanely-fast-whisper) without dependency conflicts
- you want subtitle files plus speaker attribution from local files or URLs

## When to avoid
- you need a hosted API or web UI rather than a local CLI
- you need real-time streaming transcription
- you only want a library to embed in another Python app rather than a standalone tool

## Facets
- artifact type: cli-tool
- maturity: active
- function: speech-recognition, cli, audio-processing, video-processing
- domain: speech-processing, media
- platform: windows, cli, python
- tags: whisper, transcription, speech-to-text, diarization, subtitles, yt-dlp, apple-silicon, natural-language-processing, command-line, macos, linux

## Member repositories
- zackees/transcribe-anything (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:36.314135+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:30.470187+00:00, confidence not recorded.
  - readme: https://github.com/zackees/transcribe-anything (fetched 2026-08-28T04:04:36.314135+00:00, sha c72c90eba60d)
  - homepage: https://pypi.org/project/transcribe-anything/ (fetched 2026-08-29T11:54:26.784290+00:00, sha 4b4e8fead74a)
  - registry_pypi: https://pypi.org/pypi/transcribe-anything/json (fetched 2026-08-29T11:54:26.793402+00:00, sha adaf9bd9c5a5)
- Data as of 2026-08-30T08:39:29.467469+00:00.