# souzatharsis/podcastfy

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

Repository: https://github.com/souzatharsis/podcastfy
Canonical: https://ross.abutalabs.com/products/podcastfy
Homepage: https://www.podcastfy.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: elevenlabs, gemini, genai, notebooklm, openai, podcast
Last push: 2026-05-04T14:49:10+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 80, release rhythm 40, longevity 50
- inputs: {"age_days": 702, "days_push": 121, "days_rel": 655, "gap_med": 0, "n_releases_24m": 20}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6521, forks 762 (observed 2026-08-28T04:09:44.880582+00:00)

## What it is
Podcastfy is an open-source Python package and CLI that transforms multimodal content (websites, PDFs, images, YouTube videos, topics) into engaging multilingual audio conversations using GenAI models like Gemini and OpenAI, with TTS via ElevenLabs. It serves as a programmatic, customizable alternative to NotebookLM's podcast feature.

## Use cases
- generate podcast-style audio conversations from PDFs and websites
- open source alternative to NotebookLM audio overviews
- convert YouTube videos into multilingual audio discussions
- programmatically generate AI podcasts at scale
- turn images and documents into audio dialogue
- create custom AI-generated audio content via API

## When to choose
- you need programmatic, API-driven podcast generation rather than a UI tool
- you want customization of voices, languages, and conversation style
- you need to process diverse multimodal inputs (PDFs, images, URLs, videos)
- you want to integrate audio conversation generation into your own pipeline

## When to avoid
- you need a polished no-code web interface like NotebookLM
- you cannot use paid third-party APIs (LLM and TTS providers)
- you need fully offline generation without cloud services

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, tts, speech-recognition, nlp, cli, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: notebooklm-alternative, podcast-generation, audio-conversations, multimodal, genai, elevenlabs, gemini, openai, text-to-speech, multilingual, audio, natural-language-processing, docker

## Member repositories
- souzatharsis/podcastfy (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:44.880582+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:44:25.646025+00:00, confidence not recorded.
  - readme: https://github.com/souzatharsis/podcastfy (fetched 2026-08-28T04:09:44.880582+00:00, sha e5f4a8fed05a)
  - homepage: https://www.podcastfy.ai (fetched 2026-08-29T08:40:45.988371+00:00, sha bfc29fe917eb)
- Data as of 2026-08-30T08:39:29.467469+00:00.