Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
Fix closed eyes in photos using a reference photo
Stage
Not given
Not given
Founded
Not given
Not given
Based in
SG
Not given
Pricing model
Open source
Freemium
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Free: One shared free generation across all tools with watermarked preview. Paid: 1 purchased Credit ($1.49 single) for clean full-resolution download. High Fidelity 4× downloads use 2 Credits. Credits purchased one-time with no subscription; do not expire.
Key features
82M parameter efficiency for lightweight, scalable performance
Multilingual support including English, French, Korean, Japanese, and Mandarin
Customizable voice packs with multiple lifelike voice options
Automatic content segmentation for chapter and section detection
OpenAI-compatible API endpoint for easy integration
Real-time audio generation with NVIDIA GPU acceleration
Processes up to 510 tokens in a single pass for longer audio outputs
Chrome extension for reading webpages aloud
Upload photo and select person with closed eyes
Optional reference photo of same person for guidance
Review before and after results side by side
Generate repair focused on eye area only
One person per operation
Download result as new PNG file
Works in desktop and mobile browsers
30-day photo storage and history
Google account sign-in for purchases
No subscription required
What makes it different
Outperforms larger models like XTTS (467M params) and MetaVoice (1.2B params) despite having only 82M parameters
Open-source and free for both commercial and personal use under Apache 2.0 license
Lightweight architecture enabling deployment on CPU and GPU with minimal resources
Trained on high-quality, permissively licensed audio for accurate natural-sounding speech
Designed for scalability while preserving excellent audio quality
Uses real reference photos instead of guessing eye appearance
Kokoro TTS
MomentRescue