Skip to main content
The process command is the core of NoteWise. Point it at a YouTube video URL and it fetches the transcript, sends it to your configured LLM, and writes structured Markdown study notes to your output directory.

Basic usage

notewise process "https://youtube.com/watch?v=VIDEO_ID"
Notes are written to ./output/ by default (or the directory set in your config). Each video gets its own subdirectory named after the video title.
Run notewise info "https://youtube.com/watch?v=VIDEO_ID" first to inspect the video — it shows available transcript languages, chapter count, duration, and whether it’s already cached — without triggering any processing.

Output structure

After processing, your output directory will contain:
output/
└── Video Title/
    ├── study_notes.md           # Full structured study notes
    ├── quiz.md                  # (optional, with --quiz)
    └── transcript.txt           # (optional, with --export-transcript txt)

Chapter-aware output

For videos longer than one hour that have chapters defined, NoteWise automatically splits the notes into per-chapter files instead of a single document:
output/
└── Long Course Title/
    ├── Chapter 01 - Introduction.md
    ├── Chapter 02 - Core Concepts.md
    └── Chapter 03 - Advanced Topics.md
Each chapter file is generated independently and concurrently, so long videos process faster.

All process options

--model / -m — select LLM model

Override the default model for this run. Accepts any LiteLLM-format model string.
notewise process "URL" --model gpt-4o
notewise process "URL" -m claude-3-5-sonnet-20241022
notewise process "URL" -m gemini/gemini-2.5-flash
The default model is gemini/gemini-2.5-flash. Set a persistent default via DEFAULT_MODEL in ~/.notewise/config.env.

--output / -o — output directory

Write notes to a specific directory instead of the configured default.
notewise process "URL" --output ./my-study-notes
notewise process "URL" -o /home/user/notes/chemistry
The directory is created if it does not already exist.

--language / -l — transcript language

Specify the preferred transcript language. Use standard BCP-47 language codes. The flag is repeatable — NoteWise tries each language in order and uses the first available track.
# Single language
notewise process "URL" --language en

# Prefer Spanish, fall back to English
notewise process "URL" -l es -l en

# Japanese content
notewise process "URL" -l ja
The default language list is ["en"]. Override persistently with DEFAULT_LANGUAGES in ~/.notewise/config.env.

--temperature / -t — LLM sampling temperature

Control how deterministic the LLM output is. Accepts a float from 0.0 (fully deterministic) to 1.0 (most varied). The default is 0.7.
# More consistent, structured output
notewise process "URL" --temperature 0.2

# More varied, exploratory output
notewise process "URL" -t 0.9

--max-tokens / -k — maximum tokens per response

Cap the number of tokens the LLM can generate per response. Useful when working with models that have lower limits or when you want to control cost. Defaults to the model’s own maximum.
notewise process "URL" --max-tokens 4096
notewise process "URL" -k 8192

--force / -F — re-process cached videos

By default, NoteWise skips videos it has already processed (detected via the local SQLite cache). Pass --force to rerun the full pipeline regardless.
notewise process "URL" --force
notewise process "URL" -F
Use --force after changing your prompt configuration or switching models to regenerate notes without deleting the cache.

--no-ui — plain output for CI and scripts

Disables the Rich live dashboard and prints plain progress lines to stdout instead. Recommended for CI pipelines, cron jobs, and any context where you are piping or redirecting output.
notewise process "URL" --no-ui
notewise process "URL" --no-ui >> process.log 2>&1

--quiz — generate a quiz alongside notes

In addition to study_notes.md, generate a quiz.md file containing multiple-choice questions based on the video content.
notewise process "URL" --quiz
The quiz file is written to the same video subdirectory as the study notes.

--export-transcript — export the raw transcript

Save the raw transcript to a file. Accepts either txt (plain text) or json (timestamped segments).
# Plain text transcript
notewise process "URL" --export-transcript txt

# Timestamped JSON transcript
notewise process "URL" --export-transcript json
The transcript file is written to the video’s output subdirectory alongside the study notes. Provide a Netscape-format cookie file for videos that require a signed-in YouTube session — private videos, members-only content, and age-gated videos.
notewise process "URL" --cookie-file ~/cookies.txt
notewise process "URL" --cookies /path/to/cookies.txt
See Private and restricted videos for instructions on how to export cookies from your browser.

Combining options

Options can be combined freely:
notewise process "https://youtube.com/watch?v=VIDEO_ID" \
  --model gpt-4o \
  --output ./notes \
  --language en \
  --temperature 0.3 \
  --quiz \
  --export-transcript txt \
  --no-ui

Build docs developers (and LLMs) love