Skip to main content

An Open Source alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

Project description

Podcastfy.ai 🎙️🤖

An Open Source API alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

https://github.com/user-attachments/assets/f1559e70-9cf9-4576-b48b-87e7dad1dd0b

Paper | Python Package | CLI | REST API | Web App | Feedback

Open In Colab PyPi Status PyPI Downloads Issues Pytest Docker Documentation Status License GitHub Repo stars

Podcastfy is an open-source Python package that transforms multi-modal content (text, images) into engaging, multi-lingual audio conversations using GenAI. Input content includes websites, PDFs, images, YouTube videos, as well as user provided topics.

Unlike closed-source UI-based tools focused primarily on research synthesis (e.g. NotebookLM ❤️), Podcastfy focuses on open source, programmatic and bespoke generation of engaging, conversational content from a multitude of multi-modal sources, enabling customization and scale.

Star History Chart

Audio Examples 🔊

This sample collection was generated using this Python Notebook.

Images

Audio Description Image Set
Senecio, 1922 (Paul Klee) and Connection of Civilizations (2017) by Gheorghe Virtosu Senecio, 1922 (Paul Klee) Connection of Civilizations (2017) by Gheorghe Virtosu
The Great Wave off Kanagawa, 1831 (Hokusai) and Takiyasha the Witch and the Skeleton Spectre, c. 1844 (Kuniyoshi) The Great Wave off Kanagawa, 1831 (Hokusai) Takiyasha the Witch and the Skeleton Spectre, c. 1844 (Kuniyoshi)
Pop culture icon Taylor Swift and Mona Lisa, 1503 (Leonardo da Vinci) Taylor Swift Mona Lisa

Text

Audio Description Content Type Source
Person Website Website Website
Audio Lex Fridman Podcast: Dario Amodei Anthropic's CEO Youtube Youtube
Audio Benjamin Franklin's Autobiography Youtube Book

Multi-Lingual Text

Language Content Type Description Audio Source
French Website Agroclimate research information Audio Website
Portuguese-BR News Article Election polls in São Paulo Audio Website

Features ✨

  • Generate conversational content from multiple sources and formats (images, text, websites, YouTube, and PDFs).
  • Generate shorts (2-5 minutes) or longform (30+ minutes) podcasts.
  • Customize transcript and audio generation (e.g., style, language, structure).
  • Generate transcripts using 100+ LLM models (OpenAI, Anthropic, Google etc).
  • Leverage local LLMs for transcript generation for increased privacy and control.
  • Integrate with advanced text-to-speech models (OpenAI, Google, ElevenLabs, and Microsoft Edge).
  • Provide multi-language support for global content creation.
  • Integrate seamlessly with CLI and Python packages for automated workflows.

Built with Podcastfy 🚀

Updates 🚀🚀

v0.4.0+ release

  • Released new Multi-Speaker TTS model (is it the one NotebookLM uses?!?)
  • Generate short or longform podcasts
  • Generate podcasts from input topic using grounded real-time web search
  • Integrate with 100+ LLM models (OpenAI, Anthropic, Google etc) for transcript generation

See CHANGELOG for more details.

Quickstart 💻

Prerequisites

  • Python 3.11 or higher
  • $ pip install ffmpeg (for audio processing)

Setup

  1. Install from PyPI $ pip install podcastfy

  2. Set up your API keys

Python

from podcastfy.client import generate_podcast

audio_file = generate_podcast(urls=["<url1>", "<url2>"])

CLI

python -m podcastfy.client --url <url1> --url <url2>

Usage 💻

Experience Podcastfy with our HuggingFace 🤗 Spaces app. (Note: This UI app is less extensively tested than the Python package.)

Customization 🔧

Podcastfy offers a range of customization options to tailor your AI-generated podcasts:

License

This software is licensed under Apache 2.0. See instructions if you would like to use podcastfy in your software.

Contributing 🤝

We welcome contributions! See Guidelines for more details.

Example Use Cases 🎧🎶

  • Content Creators can use Podcastfy to convert blog posts, articles, or multimedia content into podcast-style audio, enabling them to reach broader audiences. By transforming content into an audio format, creators can cater to users who prefer listening over reading.

  • Educators can transform lecture notes, presentations, and visual materials into audio conversations, making educational content more accessible to students with different learning preferences. This is particularly beneficial for students with visual impairments or those who have difficulty processing written information.

  • Researchers can convert research papers, visual data, and technical content into conversational audio. This makes it easier for a wider audience, including those with disabilities, to consume and understand complex scientific information. Researchers can also create audio summaries of their work to enhance accessibility.

  • Accessibility Advocates can use Podcastfy to promote digital accessibility by providing a tool that converts multimodal content into auditory formats. This helps individuals with visual impairments, dyslexia, or other disabilities that make it challenging to consume written or visual content.

Contributors

contributors

↑ Back to Top ↑

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

podcastfy-0.4.0.tar.gz (932.6 kB view details)

Uploaded Source

Built Distribution

podcastfy-0.4.0-py3-none-any.whl (937.8 kB view details)

Uploaded Python 3

File details

Details for the file podcastfy-0.4.0.tar.gz.

File metadata

  • Download URL: podcastfy-0.4.0.tar.gz
  • Upload date:
  • Size: 932.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.10 Linux/6.8.0-48-generic

File hashes

Hashes for podcastfy-0.4.0.tar.gz
Algorithm Hash digest
SHA256 39c7906c8c51f7da83be1df0c1cbfc7a4597713928c93060b8b5a5beb58b57a1
MD5 ef904b753c2b8a4c7cddba79f063d050
BLAKE2b-256 a21a667f2c32ab069f281df2ad651fa7c88e443a409fc222c12fe3750fe8a83f

See more details on using hashes here.

File details

Details for the file podcastfy-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: podcastfy-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 937.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.10 Linux/6.8.0-48-generic

File hashes

Hashes for podcastfy-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0490de50ae2d489ca46127ba3da69ddcda1ef77233b0c823a20cbf19da151809
MD5 040ad26013ccf3f0fb5991885c01c5a8
BLAKE2b-256 a727436688d48abf4c6ec7dba5d8ba17a2ff877743868f56ba3f29f0c2102ef7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page