Loading...
Loading...
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps, summaries, or answering questions about video content. Automatically selects the best available provider based on configured API keys - prefers full video understanding (Gemini/OpenRouter) over ASR-only providers. Supports model selection per provider.
npx skill4agent add jrusso1020/video-understand-skills video-understand# Check available providers
python3 scripts/check_providers.py
# Process a video (auto-selects best provider)
python3 scripts/process_video.py "https://youtube.com/watch?v=..."
python3 scripts/process_video.py /path/to/video.mp4
# Custom prompt
python3 scripts/process_video.py video.mp4 -p "List all products shown with timestamps"
# Use specific provider/model
python3 scripts/process_video.py video.mp4 --provider openrouter -m google/gemini-3-pro-preview
# List available models
python3 scripts/process_video.py --list-models| Priority | Provider | Capability | Env Var | Default Model |
|---|---|---|---|---|
| 1 | Gemini | Full video | | gemini-3-flash-preview |
| 2 | Vertex AI | Full video | | gemini-3-flash-preview |
| 3 | OpenRouter | Full video | | google/gemini-3-flash-preview |
| 4 | FFMPEG | Frames + ASR | None (requires ffmpeg + whisper) | scene |
| 5 | OpenAI | ASR only | | whisper-1 |
| 6 | AssemblyAI | ASR + analysis | | best |
| 7 | Deepgram | ASR | | nova-2 |
| 8 | Groq | ASR (fast) | | whisper-large-v3-turbo |
| 9 | Local Whisper | ASR (offline) | None | base |
python3 scripts/process_video.py [OPTIONS] SOURCE
Arguments:
SOURCE YouTube URL, video URL, or local file path
Options:
-p, --prompt TEXT Custom prompt for video understanding
--provider NAME Force specific provider
-m, --model NAME Force specific model
--asr-only Force ASR-only mode (skip visual analysis)
-o, --output FILE Write JSON to file instead of stdout
-q, --quiet Suppress progress messages
--list-models Show available models per provider
--list-providers Show available providers as JSON--list-modelspython3 scripts/process_video.py --list-modelsgoogle/gemini-3-flash-previewgoogle/gemini-3-pro-previewgemini-3-flash-previewgemini-3-pro-previewgemini-2.5-flashtinybasesmallmediumlargelarge-v3scenekeyframeinterval| Task | Reference |
|---|---|
| Setup & API keys | setup-guide.md |
| Use Gemini for video | gemini.md |
| Use OpenRouter | openrouter.md |
| FFMPEG frames (free) | ffmpeg-frames.md |
| ASR providers | asr-providers.md |
| Output JSON schema | output-format.md |
| Video sources & downloading | video-sources.md |
python3 scripts/setup.py # Check dependencies and API keys{
"source": {
"type": "youtube|url|local",
"path": "...",
"duration_seconds": 120.5,
"size_mb": 15.2
},
"provider": "openrouter",
"model": "google/gemini-3-flash-preview",
"capability": "full_video",
"response": "...",
"transcript": [{"start": 0.0, "end": 2.5, "text": "..."}],
"text": "Full transcript..."
}-qpip install google-generativeai # Gemini
pip install openai # OpenRouterbrew install yt-dlp ffmpeg # Video tools
pip install openai # OpenAI Whisper
pip install groq # Groq Whisper
pip install assemblyai # AssemblyAI
pip install deepgram-sdk # Deepgram
pip install openai-whisper # Local Whisper