Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
Create 21-second cafe skit videos from two photos
Stage
Not given
Not given
Founded
Not given
Not given
Based in
SG
Not given
Pricing model
Open source
Paid
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Credit packs: $9.99 for 21 credits (1 video in Standard 480p); $26.99 for 63 credits (3 videos in Standard 480p + 1 in HD 720p); $64.99 for 168 credits (8 videos in Standard 480p + 4 in HD 720p). Standard 480p costs 21 credits per 21-second video; HD 720p costs 42 credits per 21-second video. Credit
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
Two-photo portrait replacement in cafe skit template
480p Standard or 720p HD quality options
21-second vertical MP4 output
Automatic video delivery by email
Google sign-in authentication
Automated safety checks on photos
Never-expiring credit system
Automatic refund on failed generations
Private storage with automatic deletion
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
No watermark fees or hidden charges
Credits never expire and are automatically refunded on failed renders