# byjlw/video-analyzer

Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition

Repository: https://github.com/byjlw/video-analyzer
Canonical: https://ross.abutalabs.com/products/video-analyzer
Language: Python
License: Apache-2.0
License Family: permissive
Topics: asr, llms, video, video-processing
Last push: 2026-04-19T19:29:05+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 43, longevity 47
- inputs: {"age_days": 661, "days_push": 136, "days_rel": 166, "gap_med": 184.5, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1559, forks 219 (observed 2026-08-28T04:05:03.675875+00:00)

## What it is
A Python CLI tool that analyzes videos by extracting key frames, transcribing audio with Whisper, and describing content using vision LLMs like Llama 3.2 Vision via Ollama or OpenAI-compatible APIs. It can run fully locally or against cloud LLM services and outputs structured JSON analysis results.

## Use cases
- generate natural language descriptions of videos
- transcribe audio from video files
- summarize what happens in a video
- analyze video content without cloud services
- extract key frames from videos for LLM analysis
- describe surveillance or footage clips automatically

## When to choose
- you want local, private video analysis with no API keys
- you need combined visual frame analysis plus audio transcription
- you have the hardware (GPU/Apple Silicon) to run vision models locally
- you want structured JSON output of video content

## When to avoid
- you lack 16GB+ RAM or a capable GPU and cannot use cloud APIs
- you need real-time or streaming video analysis
- you need frame-accurate object detection rather than natural language descriptions

## Facets
- artifact type: cli-tool
- maturity: active
- function: video-processing, speech-recognition, llm-inference, computer-vision, nlp
- domain: machine-learning, artificial-intelligence, speech-processing, computer-vision
- platform: python, cli, cross-platform, windows
- tags: whisper, ollama, vision-language-model, frame-extraction, video-summarization, local-llm, video, macos, linux

## Member repositories
- byjlw/video-analyzer (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:03.675875+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 2026-08-30T04:29:49.681378+00:00, confidence not recorded.
  - readme: https://github.com/byjlw/video-analyzer (fetched 2026-08-28T04:05:03.675875+00:00, sha 1f6f571efaac)
- Data as of 2026-08-30T08:39:29.467469+00:00.