Hacker News new | past | comments | ask | show | jobs | submit login
Show HN: AI-Audiobook-Maker: Helping My Disabled Little Cousin Enjoy Story Books (github.com/wowitsjack)
5 points by wowitsjack on Dec 13, 2023 | hide | past | favorite | 2 comments
Hey everyone!

I've been working on a 'program"' (read as: overengineered bash script) It's called AI-Audiobook-Maker, and it was born out of my experiences with my 10-year-old cousin who is developmentally disabled. Despite his difficulties with reading, his enthusiasm for stories goes hard, even if he can't READ them.

Watching him, I realized that the world of books was kinda out of reach for him, and I suppose many others.

So, I set out to build something that could bridge this gap.

After only finding shitty, expensive subscription sites that only gave you a couple hours of audio gen, I wanted to make it a bit more accessible.

So I created a tool that can turn any text into a dope, natural sounding, engaging audiobook.

Features that make it better than using ElevenLabs or something:

- It does simple conversion of text files into audiobooks - You get a choice of six different voices and two models: tts-1 for faster processing and tts-1-hd for high-quality audio - Transparent and affordable pricing: only $0.015 per 1,000 characters

I converted 'Fuzzing The Machine', a textbook on bug hunting, and that cost around $5.

I've made it open-source in the hope that it can evolve and help more people.

Would love to hear what you think, hopefully it can help you too.

Audio Demo: https://voca.ro/1jrSMAA4WEsX

P.S (Looking for a job rn, hmu at jack<at>jackdarcy.com.au> if you'd like to chat!




This is awesome! I've been looking for something like this for the past year or so.i mostly consume audiobooks and there are a lot of books that are .epub only or have audiobooks that were recorded in the 90’s with really rough audio that make it hard to enjoy the book, this tool would be perfect for (re)creating new audiobooks. Looking forward to testing it out!

Question: how dofficult is it to put in different voice AI API support?


Aaa thank you so much!

Right now it only supports the OpenAI TTS set via the Python ospeak library, but I expect that if one were to modify the endpoints in that, it would be in theory doable! :D




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: