llm-tools-yt-transcript

Makes YouTube transcripts available to LLM

This is useful for generating a quick overview of a YouTube video before deciding to watch it

Note: this uses the youtube-transcript-api library with this caveat:

This code uses an undocumented part of the YouTube API, which is called by the YouTube web-client. So there is no guarantee that it won't stop working tomorrow, if they change how things work. I will however do my best to make things working again as soon as possible if that happens. So if it stops working, let me know!

Installation

Install this plugin in the same environment as LLM.

llm install llm-tools-yt-transcript

Usage

To use this with the LLM command-line tool:

# basic example
llm --tool yt_transcript "summarize this video: https://www.youtube.com/watch?v=kaMKInkV7Vs"  --tools-debug

# a more sophisticated report
cat yt-digest-prompt-template.txt | llm --save yt-digest
llm -t yt-digest "https://www.youtube.com/watch?v=kaMKInkV7Vs" -T yt_transcript -x > example-report.html

With the LLM Python API:

import llm
from llm_tools_yt_transcript import yt_transcript

model = llm.get_model("gpt-4.1-mini")

result = model.chain(
    "Example prompt goes here",
    tools=[yt_transcript]
).text()

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-tools-yt-transcript
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

llm install -e '.[test]'

To run the tests:

python -m pytest