Podcastfy

7.1easy start · #7of 23
in AI Podcast Generators
  • Free to practise onyes
  • Well documentedyes
  • Runs where you workno

Runs on api, self-hosted.

Podcastfy is an open-source Python package for turning source material into multilingual audio conversations with generative AI. It accepts websites, PDFs, images, YouTube videos, text, transcript files, and user-provided topics; topic generation can use grounded real-time web search. You can set the format, style, voices, language, and structure, then generate podcasts from 2–5 minutes to 30 minutes or longer. Transcript generation supports more than 100 language models, including OpenAI, Anthropic, and Google models. Listed text-to-speech options include OpenAI, Google, ElevenLabs, and Microsoft Edge. Local language models are also supported for transcript generation, which the project describes as offering more privacy and control. Audio exports as MP3. Podcastfy offers Python package and command-line use, plus a beta FastAPI service for URLs. It is free under the Apache 2.0 license. Getting started requires Python 3.11 or higher and ffmpeg; API key needs depend on the selected models, though a documented local-model and Edge TTS setup requires no keys.

Who it is for

Podcastfy may suit content creators, educators, researchers, and accessibility advocates who want to turn varied source material into audio conversations. It also fits users comfortable setting up a Python package or CLI.

What is good

  • Accepts websites, PDFs, images, video, text, transcripts, and topics.
  • Supports short and longform podcast generation.
  • Offers customizable format, style, voices, language, and structure.
  • Exports audio as MP3.
  • A documented local-model setup requires no API keys.

What to know first

  • Requires Python 3.11 or higher and ffmpeg.
  • API keys may be needed, depending on selected models.
  • Google multispeaker TTS is limited to English and needs extra setup.
  • FastAPI deployment is documented as beta.

Verdict

Podcastfy offers a flexible way to turn different inputs into multilingual audio, with both hosted-model and local-model options. Check the setup requirements and model-specific key needs before choosing an implementation.

Podcastfy plans and pricing

All plans
Podcastfy open-source Python package Free No paid plan or usage allowance is stated on the opened maker pages. github.com · 8 Oct 2026

Compared on AI podcast generators

Free plan
Yes
Host dialogue
Yes
Source imports
websites, PDFs, images, YouTube videos, topics, raw text, transcript files
Audio export
mp3

Best Podcastfy alternatives

See all 20