Hey everyone, I wanted to share a tool I've been working on called Abogen that might be a game-changer for anyone interested in converting text to speech quickly.

What is Abogen?

Abogen is a powerful text-to-speech conversion tool that transforms ePub, PDF, or text files into high-quality audio with perfectly synced subtitles in seconds. It uses the incredible Kokoro-82M model for natural-sounding voices.

Why you might love it:

• 🏠 Fully local: Works completely offline - no data sent to the cloud, great for privacy and no internet required! (kokoro sometimes uses the internet to download models)
• 🚀 FAST: Processes ~3,000 characters into 3+ minutes of audio in just 11 seconds (even on a modest GTX 2060M laptop!)
• 📚 Versatile: Works with ePub, PDF, or plain text files (or use the built-in text editor)
• 🎙️ Multiple voices/languages: American/British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese
• 💬 Perfect subtitles: Generate subtitles by sentence, comma breaks, or word groupings
• 🎛️ Customizable: Adjust speech rate from 0.1x to 2.0x
• 💾 Multiple formats: Export as WAV, FLAC, or MP3

Perfect for:

• Creating audiobooks from your ePub collection
• Making voiceovers for Instagram/YouTube/TikTok content
• Accessibility tools
• Language learning materials
• Any project needing natural-sounding TTS

It's super easy to use with a simple drag-and-drop interface, and works on Windows, Linux, and MacOS!

How to get it:

It's open source and available on GitHub: https://github.com/denizsafak/abogen

I'd love to hear your feedback and see what you create with it!