Skip to main content
This guide is optimized for first-time setup. You only need to run setup once — all subsequent runs use the saved config.
1

Install notewise

uv tool install notewise
Need pip or Docker instead? See Installation.
2

Get an API key

The default model is Gemini 2.5 Flash — free tier, no billing required.
  1. Visit aistudio.google.com/app/apikey
  2. Create a new API key
  3. Copy it for the next step
Any supported provider works. See LLM Providers for OpenAI, Anthropic, Groq, and more.
3

Run the setup wizard

notewise setup
The interactive wizard prompts for your provider and API key, then writes ~/.notewise/config.env. Run this once.
4

Process a video

notewise process "https://youtube.com/watch?v=VIDEO_ID"
A live progress dashboard shows while notewise fetches the transcript and generates notes. When finished, open ./output/ to find your Markdown study notes.

​
Example session

$ notewise process "https://youtube.com/watch?v=dQw4w9WgXcQ"

 notewise  v1.0.0

Processing 1 video...

 Video Title
   ✔ Metadata fetched
   ✔ Transcript fetched  (en, 342 segments)
   ✔ Notes generated  (3 chunks)
   ✔ Written → output/Video Title.md

────────────────────────────────────────
  1 processed · 0 failed · 12.4s · $0.0004

​
What to try next

Process a playlist

Process entire YouTube playlists with concurrent processing.

Generate a quiz

Auto-generate 10-15 multiple choice questions with answers.

Switch LLM model

Use OpenAI, Anthropic, Groq, or any LiteLLM-supported model.

Batch file

Process multiple URLs from a text file.
notewise process "https://youtube.com/playlist?list=PLAYLIST_ID"
If a run fails, start with notewise doctor → notewise config → notewise logs --tail 80. See Troubleshooting for the full guide.
Last modified on March 28, 2026