# lamm-mit/PDF2Audio

Repository: https://github.com/lamm-mit/PDF2Audio
Canonical: https://ross.abutalabs.com/products/pdf2audio
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2025-04-18T11:10:42+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 17, release rhythm 35, longevity 50
- inputs: {"age_days": 710, "days_push": 502, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1383, forks 175 (observed 2026-08-28T04:04:34.626720+00:00)

## What it is
A Gradio-based web application that converts PDF documents into audio podcasts, lectures, and summaries using OpenAI GPT models for text generation and text-to-speech. Users can upload multiple PDFs, choose instruction templates, select voices, and iteratively edit the generated transcript.

## Use cases
- convert a pdf into a podcast
- turn research papers into audio lectures
- generate audio summaries of documents
- create a notebooklm-style podcast from pdfs
- edit and refine a podcast transcript before generating audio
- choose different voices for podcast speakers

## When to choose
- you want a ready-made web UI for turning PDFs into spoken audio
- you already have an OpenAI API key and want GPT-based script generation
- you want to iterate on transcripts with comments before rendering audio

## When to avoid
- you need fully offline or self-hosted TTS without API costs
- you need a CLI or batch pipeline rather than an interactive app
- you need non-OpenAI LLM or TTS providers

## Facets
- artifact type: application
- maturity: active
- function: tts, nlp, llm-inference, pdf, audio-processing
- domain: pdf, artificial-intelligence, developer-tools
- platform: python, cross-platform, self-hosted
- tags: pdf-to-audio, podcast-generation, gradio, openai, text-to-speech, lecture-generation, hugging-face-spaces, natural-language-processing, audio, web-server

## Member repositories
- lamm-mit/PDF2Audio (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:34.626720+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 2026-08-30T04:40:02.955725+00:00, confidence not recorded.
  - readme: https://github.com/lamm-mit/PDF2Audio (fetched 2026-08-28T04:04:34.626720+00:00, sha 53db0d08c486)
- Data as of 2026-08-30T08:39:29.467469+00:00.