Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
AI meme and dance video generator using photo templates
Stage
Not given
Startup
Founded
Not given
2026
Based in
SG
HK
Pricing model
Open source
Freemium
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Single pack: $9.90 for 50 credits (2 standard 480p clips at $4.95 each or 1 full-length 720p clip). Creator pack: $24.90 for 150 credits. Studio pack: $59.90 for 400 credits. Standard clips cost 25 credits at 480p, 50 at 720p, 100 at 1080p. Templates longer than 15 seconds cost 50, 100 and 150 credi
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
Ready-made scene templates with motion and audio pre-synced
Watermark-free MP4 exports at 480p, 720p and 1080p resolutions
Original audio synced to video action
Vertical 9:16 format optimized for TikTok, Instagram Reels and YouTube Shorts
One-time credit packs that never expire
Pet-friendly templates for cats and dogs
Automatic credit refund on failed generation
Support for 1 or 2 photos depending on template
Generation typically takes 5-15 minutes
Available in 5 languages: English, Spanish, Japanese, Korean and Simplified Chinese
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
Template-first workflow with no custom prompts or motion reference needed
Every video includes original trend audio precisely synced to action
No subscription required; one-time credits never expire
Uses Seedance 2.5 AI model for photo-to-video generation
Kokoro TTS
TrendSwap