How azzedde/paper_to_podcast works
Paper-to-Podcast is a command-line tool that turns a research-paper PDF into a three-person conversational script and then a merged podcast MP3. The workflow extracts paper text, plans sections, generates an introduction and retrieval-grounded section dialogue, refines the script, synthesizes each persona’s voice, and merges the audio. The README also documents the planning, discussion, enhancement, and text-to-speech capabilities. Edges reflect the sampled entry point and script/audio modules; unsampled internals are not inferred.
Main entry points: script.py Script workflow · paper_to_podcast.py Prompt chains · audio_gen.py Audio workflow · templates.py Planning prompt
Components 18
Podcast workflow
- CLI entry point
paper_to_podcast.py
Script generation
- Script workflow
utils/script.py - PDF extraction
utils/script.py - Prompt chains
paper_to_podcast.py - Planning prompt
templates.py - Introduction prompt
templates.py - Discussion prompt
templates.py - Enhancement prompt
templates.py - Plan parser
utils/script.py
Context retrieval
- Retrieval context
utils/script.py
Audio production
- Audio workflow
utils/audio_gen.py - Persona voice synthesis
utils/audio_gen.py - MP3 merge
utils/audio_gen.py
Other components
- User
- Research PDF
- OpenAI language models
- OpenAI speech API
- Podcast MP3
Connections 19
- User → CLI entry point: runs
README.md - User → Research PDF: provides
README.md - Research PDF → CLI entry point: input path
README.md - CLI entry point → Script workflow: generates script
paper_to_podcast.py - CLI entry point → Audio workflow: generates audio
paper_to_podcast.py - Script workflow → PDF extraction: extracts text
utils/script.py - Script workflow → Prompt chains: invokes chains
utils/script.py - Prompt chains → Planning prompt: uses
paper_to_podcast.py - Prompt chains → Introduction prompt: uses
paper_to_podcast.py - Prompt chains → Enhancement prompt: uses
paper_to_podcast.py - Prompt chains → Plan parser: parses plan
paper_to_podcast.py - Script workflow → Retrieval context: builds context
utils/script.py - Script workflow → Discussion prompt: generates dialogue
utils/script.py - Retrieval context → OpenAI language models: embeds text
utils/script.py - Script workflow → OpenAI language models: generates script
- Audio workflow → Persona voice synthesis: dispatches lines
utils/audio_gen.py - Persona voice synthesis → OpenAI speech API: synthesizes speech
utils/audio_gen.py - Audio workflow → MP3 merge: merges files
utils/audio_gen.py - MP3 merge → Podcast MP3: exports MP3
utils/audio_gen.py