Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
Generate an 8-second viral Topo Gigio celebration video from a single photo in 720p, keeping your face, hair and original clothes.
Stage
Not given
Startup
Founded
Not given
2026
Based in
SG
Not given
Pricing model
Open source
Paid
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Single Video Pass: $9.90 for 1 video (100 credits). Creator 5-Video Pack: $29.90 for 5 videos (500 credits, $5.98 per video). Viral Studio 12-Pack: $59.99 for 12 videos (1,200 credits, $5.00 per video). One-time payment, no subscription. Failed renders automatically refunded.
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
Full person replacement with original clothes preserved
8-second 720p MP4 video output
Choice of 9:16 vertical or 16:9 wide format
Stadium crowd audio included
Watermark-free downloads
Free re-roll request for distorted results
Automatic refund on failed renders
Credits never expire
About 2 minutes render time
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
Preserves original clothing instead of placing user in a football shirt
Replaces entire foreground person shot-by-shot, not just face-swap
Native 9:16 vertical format keeps both elbows in frame
Purpose-built template with proper hand gesture anatomy
Kokoro TTS
Enzo Celebration AI