Skip to main content

Playlist Summarizer

A monorepo containing tools for fetching YouTube playlist transcripts and generating AI-powered summaries using local or cloud-based LLM models via Ollama.

Packages

Package Description
playlist-summarizer-core Core library for transcript fetching and AI summarization
playlist-summarizer-cli Command-line interface for the summarizer

Features

  • 📥 Fetch Playlists: Download transcripts from YouTube playlists
  • 🤖 AI Summarization: Generate summaries using Ollama models (local or cloud)
  • 📝 Markdown Output: Clean, structured summaries in Markdown format
  • 🎯 Selective Processing: Choose which videos to summarize
  • 📊 Progress Tracking: Real-time progress bars and status updates
  • 🔒 Secure Prompts: Hardened system prompts resistant to injection attacks
  • 🎨 Rich CLI: Beautiful terminal interface with colors and formatting

Requirements

  • Python 3.14+
  • Ollama installed and running (for local models)
  • Or Ollama Cloud API key (for cloud models)

Quick Start

  1. Clone the repository:
git clone https://github.com/ajxd2/playlist-summarizer.git
cd playlist-summarizer
  1. Install dependencies using uv:
uv sync
  1. (Optional) Set up environment variables:
cp .env.example .env
# Edit .env and add:
# OLLAMA_HOST=http://localhost:11434  # Optional, defaults to localhost
# OLLAMA_API_KEY=your_api_key_here     # Required for cloud models
  1. Run the CLI:
uv run playlist-summarizer

Project Structure

playlist-summarizer/
├── packages/
│   ├── core/                    # Core library
│   │   ├── src/
│   │   │   └── playlist_summarizer_core/
│   │   │       ├── __init__.py
│   │   │       ├── fetcher.py   # YouTube transcript fetching
│   │   │       └── summarizer.py # AI summarization logic
│   │   ├── pyproject.toml
│   │   └── README.md
│   └── cli/                     # CLI application
│       ├── src/
│       │   └── playlist_summarizer_cli/
│       │       ├── __init__.py
│       │       ├── __main__.py
│       │       └── main.py      # CLI entry point
│       ├── pyproject.toml
│       └── README.md
├── transcripts/                 # Downloaded transcripts (gitignored)
├── summaries/                   # Generated summaries (gitignored)
├── pyproject.toml               # Workspace configuration
├── uv.lock                      # Dependency lock file
└── README.md

Usage

Using the CLI

Run the CLI application:

uv run playlist-summarizer

Fetch Playlist Transcripts

  1. Select "Fetch playlist" from the main menu
  2. Enter the YouTube playlist URL
  3. Specify the output directory (defaults to transcripts/{playlist_id}/)
  4. Transcripts will be saved as .txt files

Summarize Playlists

  1. Select "Summarize playlist" from the main menu
  2. Enter the directory path containing transcripts (defaults to transcripts/)
  3. Choose the Ollama model to use (e.g., gemma3:4b, llama3.1:8b, qwen2.5:7b)
  4. Specify the output directory for summaries (defaults to summaries/)
  5. Select a playlist folder
  6. Choose which videos to summarize (use space to select/deselect)
  7. Optionally create a master summary of all video summaries

Using the Core Library

from playlist_summarizer_core import get_playlist_videos, get_transcript, Summarizer

# Fetch transcripts
videos = get_playlist_videos("https://www.youtube.com/playlist?list=...")
for video in videos:
    transcript = get_transcript(video)
    print(f"{video.title}: {len(transcript)} characters")

# Summarize content
summarizer = Summarizer(model="gemma3:4b")
summary = summarizer.summarize("Your transcript text...")

Configuration

Environment Variables

  • OLLAMA_HOST - Ollama server URL (default: http://localhost:11434)
  • OLLAMA_API_KEY - API key for Ollama Cloud (required for cloud models)

Default Directories

  • Transcripts: transcripts/
  • Summaries: summaries/

Development

Setup Development Environment

uv sync

Run from Source

# Run CLI
uv run playlist-summarizer

# Or run as module
uv run python -m playlist_summarizer_cli

Working with Individual Packages

# Work on core package
cd packages/core
uv sync

# Work on CLI package
cd packages/cli
uv sync

License

MIT License - see LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request. See CONTRIBUTING.md for guidelines.

Author

Anthony Kovach - aj@ajxd2.dev

Metadata

Release files for playlist-summarizer 0.1.0

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

Source distribution (sdist)

Source distribution for playlist-summarizer 0.1.0
File Size Uploaded Provenance Actions
playlist_summarizer-0.1.0.tar.gz 3.7 kB Without provenance Details for playlist_summarizer-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for playlist-summarizer 0.1.0
File Interpreter ABI Platform Actions
playlist_summarizer-0.1.0-py3-none-any.whl Python 3 none any Details for playlist_summarizer-0.1.0-py3-none-any.whl

Total release size: 7.7 kB

Release files / playlist_summarizer-0.1.0.tar.gz

Download URL playlist_summarizer-0.1.0.tar.gz
Size 3.7 kB
Tags Source
SHA-256 checksum
How to use checksums
d4cf083e94b434630618b6443080a11dd5751facc57c6f6ba62809638309c156
BLAKE2b-256 checksum
How to use checksums
95e1d2ffdd9da9284727af7fe970f5e6e41cbe86fdf40b82c4e01d7885691a21
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / playlist_summarizer-0.1.0-py3-none-any.whl

Download URL playlist_summarizer-0.1.0-py3-none-any.whl
Size 4.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c197dfe5464066850dc4f1abfe4d007401c1d20a7210caa96d5a4aeabd1ed8f4
BLAKE2b-256 checksum
How to use checksums
fc9880cb453d291730e2a0a74564e648a5faf1ee663740f2e2a998bf13416bec
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for playlist-summarizer 0.1.0

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

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

0.1.0 This release

2 release files No 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