souzatharsis

podcastfy: Turn Multimodal Sources into AI Podcast Conversations

Podcastfy is a Python package and CLI for turning web pages, PDFs, images, YouTube videos, and topics into multilingual, conversational audio. It suits creators and teams that want to customize or automate podcast generation, but its recent maintenance activity is quiet.

QuietPythonApache-2.0AILibraryText To Speech
View on GitHub Compare
Stars
6.6k
Forks
765
Stars, last 30 days
+165
Last commit
5 months ago
Contributors
16

Our take

Quietno commits in the last 90 days and no release in a year

Health score

26/100

How it is scored
Activity
19
Community
44
Issues
21
Pull requests
20

+165 stars in the last 30 days

Podcastfy is a flexible, developer-oriented route from multimodal source material to customizable podcast audio, though its current quiet maintenance status makes adoption worth evaluating carefully.

Good fit if

  • You need a Python package or CLI to generate audio conversations from URLs, PDFs, images, videos, or topics.
  • You want control over conversation style, language, transcript models, or speech providers.
  • Your workflow can accommodate Python 3.11+, FFmpeg, and the API credentials required by your chosen providers.

Look elsewhere if

  • You need evidence of active recent releases or issue and pull-request handling before adopting a dependency. The project has had no recent commits, releases, or recorded issue closures and PR merges in the measured period.
  • You want a ready-made, fully supported end-user podcast application rather than a package and CLI with a separate beta API option.
  • Your use case does not involve generating conversational audio from source material.
All health signals
Last commit2026-05-04 (5 months ago)
Commits, last 90 days0
Releases, last 12 months0 (latest v0.4.0, 2024-11-16)
Contributors16 (top contributor: 75% of commits)
Issues closed, last 90 days0
Pull requests merged, last 90 days0
Project age2 years

Checked on 2026-10-08 with the GitHub API.

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

6,813

Forks

792

Change since Nov 15, 2026: +6 stars·0 forks

Overview

Podcastfy turns text and image-based sources, including websites, PDFs, images, and YouTube videos, into AI-generated podcast conversations. It addresses the gap between research-summary interfaces and workflows that need programmatic, customizable audio generation.

The Python package and CLI let users shape conversation style, structure, and language, and connect transcript generation and text-to-speech providers. It is aimed at developers and content teams who want to create short or long-form audio from varied sources, rather than simply listen to a fixed-format summary.

Key Features

  • Accepts websites, PDFs, images, YouTube videos, text, and user-provided topics as inputs.
  • Generates short or long-form conversational podcasts.
  • Supports transcript generation through multiple hosted LLM providers and local models.
  • Offers configurable conversation format, style, voices, and language.
  • Integrates text-to-speech providers including OpenAI, Google, ElevenLabs, and Microsoft Edge.
  • Provides Python and CLI interfaces for scripted workflows.
  • Includes a beta FastAPI option for URL-based requests and Docker support.

Use Cases

  • A content creator can turn articles or blog posts into audio for audiences who prefer listening.
  • An educator can convert lecture notes and visual materials into conversational audio for students.
  • A researcher can make accessible audio versions of papers or technical material for broader audiences.
  • A team with a multilingual audience can generate audio conversations from source material in supported languages.
  • A developer can automate podcast creation from a set of URLs using the Python API or CLI.

What you need

Detected in the repository

  • Python (from pyproject.toml)
  • A Dockerfile, so it can run in a container; a Compose file sets up the related services
  • A test suite and automated checks on GitHub Actions

License in plain words

Apache-2.0permissive

  • Commercial use: yes
  • Modify and redistribute: yes
  • You must keep: the license, the NOTICE file and a note of your changes
  • Share your changes: no
  • Includes an explicit patent grant from the contributors:

A summary, not legal advice: the LICENSE file is what applies.

Getting Started

Install the package and generate audio from URLs:

pip install podcastfy
from podcastfy.client import generate_podcast

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

See the repository README for API key setup, configuration, and CLI instructions.

Alternatives

  • open-notebooklm: Open NotebookLM turns PDFs into podcast dialogue and MP3s, while Podcastfy supports broader inputs such as web pages, images, and YouTube videos.
ProjectLanguageLicenseStarsStatus
podcastfyPythonApache-2.06.6kQuiet
open-notebooklmPythonApache-2.02.6kInactive

Considerations

  • The project is marked quiet: it has no commits in the measured recent period and no release in over a year. The measured data also shows no issues closed or pull requests merged in that period, so teams should assess how they will handle maintenance needs.
  • The README requires Python 3.11 or higher and FFmpeg for audio processing. Generation also depends on configuring API keys for the providers you use; local LLMs are offered as an option for transcript generation.
  • The FastAPI path is explicitly described as beta and currently focused on URLs.
  • The README describes broad provider and content support, but does not establish that every provider or input type has identical behavior. Validate the combinations your workflow depends on.
  • The project uses the Apache-2.0 license. Review its terms and the separate license guide before incorporating it into software.

Found this useful?

Share it with someone who would like podcastfy.

Comparisons