Skip to main content

llm-fragments-youtube-transcript

A fragment loader for LLM that converts youtube transcripts into plaintext using youtube-transcript-api and yt-dlp.

yt-dlp is used for metadata (title, uploader, date, description) and youtube-transcript-api is used to fetch the transcript. yt-dlp at time of writing can only write subs to disk.

PyPI Changelog License

To do

  • Chat mode
  • Embedding generation

Installation

Install this plugin in the same environment as LLM:

llm install llm-fragments-youtube-transcript

Usage

Use -f 'yt:URL' to fetch and convert an online video transcript to plaintext.

Example:

llm -f 'yt:https://youtube.com/?v=' "Summarize this video."

The output includes:

  • Title
  • Uploader
  • Date
  • Description
  • Transcription

Development

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

cd llm-fragments-youtube-transcript
uv sync
source .venv/bin/activate

Dependencies

Metadata

Release files for llm-fragments-youtube-transcript 0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llm-fragments-youtube-transcript 0.1
File Size Uploaded Provenance
llm_fragments_youtube_transcript-0.1.tar.gz 4.0 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for llm-fragments-youtube-transcript 0.1
File Interpreter ABI Platform
llm_fragments_youtube_transcript-0.1-py3-none-any.whl Python 3 none any Details

Total release size: 8.8 kB

Release files / llm_fragments_youtube_transcript-0.1.tar.gz

Download URL llm_fragments_youtube_transcript-0.1.tar.gz
Size 4.0 kB
Tags Source
SHA-256 checksum
How to use checksums
0186434ded259e99fdc0da9d0aab480a22c281da55798753949b2c2ccb883cec
BLAKE2b-256 checksum
How to use checksums
87b0a8684de1d14adf8fde4915e40fdf934621a71dd348469b3344a140133c01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 5, 2025.

Transparency log

Release files / llm_fragments_youtube_transcript-0.1-py3-none-any.whl

Download URL llm_fragments_youtube_transcript-0.1-py3-none-any.whl
Size 4.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8010c111dd8b50050aa4be79f9fb5243d10f60831f69141bca58be2128c9a55d
BLAKE2b-256 checksum
How to use checksums
bb75e18e82b154c22750f23db0b0fb44810fb162a4a6443f3d764bf3cd11407a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 5, 2025.

Transparency log

Security for llm-fragments-youtube-transcript 0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for llm_fragments_youtube_transcript-0.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 5, 2025.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page