Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
Real-time AI face swap in your browser, no download or GPU required
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.
Live Face Swap: 30 credits per minute, billed by the second. New accounts get 20 seconds free. Starter Pack $9 for 600 credits (≈20 live minutes). Creator Pack $35 for 2500 credits (≈83 live minutes). Studio Pack $90 for 7000 credits. Credits valid for 365 days.
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
Real-time character swapping with face, hair and outfit transformation
Restyle entire scene into fantasy, anime, toon or clay art styles
Browser-based with no app download or GPU required
Works on desktop and mobile browsers with camera access
Expressions and gestures tracked in real time
Free camera preview with no account required
Support for JPG, PNG and WebP reference images up to 5 MB
Sessions run up to 10 minutes or until balance runs out
Billing by the second, no hidden charges
No recording of camera feed or personal data
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
Cloud-based real-time processing means no GPU or software installation needed
Transforms entire character including hair and outfit, not just the face
Flexible pay-as-you-go credit system with no mandatory subscription
Works across multiple AI video and image creation tools in one platform
Easy switching between characters and styles within a single session
Kokoro TTS