Earkind: The AI Podcast Generator
Earkind is an AI-powered tool designed to create engaging podcasts using neural expressive text-to-speech and programmatic audio editing. By simply providing a .txt file with a selection of plain text and a list of recent Arxiv papers as URLs, Earkind generates a full podcast episode and description based on the provided content.
One of the unique features of Earkind is the ability to define characters for the podcast, including the overly hyped and earnest tech bro host Giovanni Pete Tizzano, sarcastic analyst Robert, and witty research expert Belinda. This creates an organized conversation between the characters, with scripts created for each section, and the program parsing them accordingly.
After recording is complete, Earkind offers a variety of jingles, sound effects, and background music to enhance the podcast. The tool automatically adjusts volumes, overlays sections, and combines narrations and audios using Pydub.
Earkind also generates timestamps and descriptions for each episode, making it convenient for listeners to navigate through the content. The titles and overall description are generated by ChatGPT as well.
Earkind has the potential to create personalized audio content and the team behind it welcomes feedback and suggestions from users. There are also plans to make the code public and provide an in-depth explanation of the design thinking behind the tool.
