Skip to main content

Podcast-LLM: AI-Powered Podcast Generation

Tests codecov GitHub stars GitHub Downloads GitHub issues License: CC BY-NC 4.0

An intelligent system that automatically generates engaging podcast conversations using LLMs and text-to-speech technology.

View Documentation

Features

  • Two modes of operation:
    • Research mode: Automated research and content gathering using Tavily search
    • Context mode: Generate podcasts from provided source materials (URLs and files)
  • Dynamic podcast outline generation
  • Natural conversational script writing with multiple Q&A rounds
  • High-quality text-to-speech synthesis using Google Cloud or ElevenLabs
  • Checkpoint system to save progress and resume generation
  • Configurable voices and audio settings
  • Gradio UI

Examples

Listen to sample podcasts generated using Podcast-LLM:

Structured JSON Output from LLMs (Google multispeaker voices)

Play Podcast Sample

UFO Crash Retrieval (Elevenlabs voices)

Play Podcast Sample

The Behenian Fixed Stars (Google multispeaker voices)

Play Podcast Sample

Podcast-LLM Overview (Google multispeaker voices)

Play Podcast Sample

Robotic Process Automation (Google voices)

Play Podcast Sample

Web Interface

Gradio Web Interface

Installation

  1. Install using pip:

    pip install podcast-llm
    
  2. Set up environment variables in .env:

    OPENAI_API_KEY=your_openai_key
    GOOGLE_API_KEY=your_google_key 
    ELEVENLABS_API_KEY=your_elevenlabs_key
    TAVILY_API_KEY=your_tavily_key
    ANTHROPIC_API_KEY=your_anthropic_api_key
    

Usage

  1. Generate a podcast about a topic:

    # Research mode (default) - automatically researches the topic
    podcast-llm "Artificial Intelligence"
    
    # Context mode - uses provided sources
    podcast-llm "Machine Learning" --mode context --sources paper.pdf https://example.com/article
    
  2. Options:

    # Customize number of Q&A rounds per section
    podcast-llm "Linux" --qa-rounds 3
    
    # Disable checkpointing
    podcast-llm "Space Exploration" --checkpoint false
    
    # Generate audio output
    podcast-llm "Quantum Computing" --audio-output podcast.mp3
    
    # Generate Markdown output
    podcast-llm "Machine Learning" --text-output podcast.md
    
  3. Customize voices and other settings in config/config.yaml

  4. Launch the Gradio web interface:

    # Start the web UI
    podcast-llm-gui
    

    This launches a user-friendly web interface where you can:

    • Enter a podcast topic
    • Choose between research and context modes
    • Upload source files and URLs for context mode
    • Configure Q&A rounds and checkpointing
    • Specify output paths for text and audio
    • Monitor generation progress in real-time

License

This project is licensed under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)

This means you are free to:

  • Share: Copy and redistribute the material in any medium or format
  • Adapt: Remix, transform, and build upon the material

Under the following terms:

  • Attribution: You must give appropriate credit, provide a link to the license, and indicate if changes were made
  • NonCommercial: You may not use the material for commercial purposes
  • No additional restrictions: You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits

For commercial use, please contact evandempsey@gmail.com to obtain a commercial license.

The full license text can be found at: https://creativecommons.org/licenses/by-nc/4.0/legalcode

Acknowledgements

This project was inspired by podcastfy, which provides a framework for generating podcasts using LLMs.

This implementation differs by automating the research and content gathering process, allowing for fully autonomous podcast generation about any topic without requiring manual research or content curation.

Metadata

Release files for podcast-llm 0.2.2

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

Source distribution (sdist)

Source distribution for podcast-llm 0.2.2
File Size Uploaded Provenance Actions
podcast_llm-0.2.2.tar.gz 36.6 kB Without provenance Details for podcast_llm-0.2.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for podcast-llm 0.2.2
File Interpreter ABI Platform Actions
podcast_llm-0.2.2-py3-none-any.whl Python 3 none any Details for podcast_llm-0.2.2-py3-none-any.whl

Total release size: 83.5 kB

Release files / podcast_llm-0.2.2.tar.gz

Download URL podcast_llm-0.2.2.tar.gz
Size 36.6 kB
Tags Source
SHA-256 checksum
How to use checksums
492e79de5edfcbeb0d2d6d6e7edd5ce9ff145e2f0c9f6074070a9ca10f5eba14
BLAKE2b-256 checksum
How to use checksums
31c8ae769941f83f94a8d2efa155b599b870592ca9274258c720eedb8a829a08
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.8.5 CPython/3.12.7 Linux/6.5.0-1025-azure

Release files / podcast_llm-0.2.2-py3-none-any.whl

Download URL podcast_llm-0.2.2-py3-none-any.whl
Size 46.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
dacff98c3cd12e5857bced192a9954fdafe5cea06a8a4be273b607862b85160a
BLAKE2b-256 checksum
How to use checksums
399fb5e6f414f1804cb8b64c2f172142cce475fe65010331653a1889bbf5a3e7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.8.5 CPython/3.12.7 Linux/6.5.0-1025-azure

Security for podcast-llm 0.2.2

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.

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