Echo

• 

  Thumbnail

• 

  Listen to audiobook

• 

  Home screen

Inspiration

Over half of all readers listen to the audiobooks. Yet, only 9% of books are available as audiobooks - and that's doesn't count other written content, like articles, research papers, or blog posts.

What it does

Echo takes any epub or PDF, cleans up any artifacts like footers/headers/page numbers, and turns it into an high quality audiobook within minutes - so you can listen to the latest research paper on your commute.

Beyond this, you can TALK to Echo audiobooks. If you have a question about some confusing content, want to dive deeper into a concept, or even just define a word, you can ask Echo, which will respond with context from what you've been listening to :)

How we made it

We use React and PDF libraries to extract text from PDFs and EPUBs

Because PDF has a more flexible format, the text extracted from the PDF is often messy, so we created a text cleaner with Google Gemini 2.0 that removes unwanted elements, like:

• Page numbers
• Headers and footers
• Copyright notices
• Formatting artifacts Books can be very large, so the text cleaner breaks the book up into many 1000 word chunks and cleans them in parallel in order to reduce latency.

After we get the fully cleaned text, we convert it to audio using ElevenLabs. We stream the audio back to the user in chunks so they can start listening right away (as opposed to when everything is done generating.

For the interactive audiobook feature, we built a context-aware system that tracks what users are currently listening to. This powers Echo's interactive features, allowing users to ask questions about the content and receive relevant responses based on their current position in the audiobook.

Built With

• elevenlabs
• gemini
• mistral
• next.js
• openai
• react
• realtimeapi
• tailwind