DocsPodcast vs Podcastfy

DocsPodcast is a free, MIT-licensed project that turns uploaded documents into AI-generated, multi-speaker podcast conversations and answers questions about their contents. It accepts PDF, DOCX, DOC, and TXT files, with uploads limited to 0.5 MB (512 KB). Its retrieval pipeline stores document chunks in ChromaDB for semantic search and grounds answers in the source material. Podcast scripts support conversations between two and four speakers, combining generated segments into one MP3 file. The documented providers are OpenRouter with GPT-4o-mini, Google Gemini as a fallback, Gemini TTS, and gTTS as a speech fallback. English and Arabic are listed for question answering, scripts, and audio. The responsive interface works on mobile and desktop and renders Markdown tables, code blocks, blockquotes, and lists. Deployment documentation covers local hosting with Python 3.9+ and required OpenRouter and Google Gemini API keys. It is available for self-hosted, web, and Windows use, with a linked live demo.

Podcastfy is a free, open-source Python package that turns multimodal source material into multilingual audio conversations with generative AI. It accepts websites, PDFs, images, YouTube videos, raw text, transcript files and user-provided topics; topic generation can use grounded real-time web search. Users can set the podcast format, style, voices, language and structure, then generate short episodes of 2–5 minutes or longform episodes of 30 minutes or more. Transcript generation supports more than 100 language-model options, including OpenAI, Anthropic and Google models. Listed speech engines include OpenAI, Google, ElevenLabs and Microsoft Edge. Local language models are supported for transcript generation, offering the project’s stated privacy and control benefits. Usage is available through a Python package, command-line interface and beta FastAPI service for URLs, with MP3 audio export. API-key needs depend on selected models; a documented local-model and Edge TTS setup requires none. Python 3.11 or higher and ffmpeg are required. The project uses the Apache 2.0 license.