A fork from (https://github.com/lamm-mit/PDF2Audio, working with OpenRouter API in Colab environment.
Before running, make sure to set your OpenRouter API key in the Colab environment variables or enter it in the provided text box when running the app.
- Upload multiple PDF files
- Choose from different instruction templates (podcast, lecture, summary, etc.)
- Customize text generation and audio models
- Select different voices for speakers
- Iterate on the draft via specific or general commments, and/or edits to the transcript and specific feedback to the model for improvements
- Integrate with OpenRouter API
- Leverage capability and resource of Google Colab
This app should launch the Gradio interface within Colab, allowing users to upload PDFs and generate audio podcasts based on their content.
This project was inspired by and based on the code available @ https://github.com/knowsuchagency/pdf-to-podcast, https://github.com/knowsuchagency/promptic, https://github.com/lamm-mit/PDF2Audio.