Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
Immersive experiences on any device with depth and spatial presence
Stage
Not given
Established
Founded
Not given
2014
Based in
SG
US
Pricing model
Open source
Freemium
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Immersity for Mobile is free with watermark. Immersity for Web offers paid monthly subscriptions that auto-renew; monthly subscriptions can be cancelled or upgraded at any time and remain valid until one month from purchase date.
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
Switchable-Display Hardware for converting standard and immersive modes without resolution loss
Spatial Tracking that adjusts immersive content based on primary viewer position
Support for wide range of image formats including PNG, JPG, HEIC, WEBP
Video format support for mp4, mkv, and mov files
Depth map generation with 16-bit precision
Apple Music® Album Motion export format support
Account management with unified access to Mobile and Web apps
Immersive Motion and 3D Image conversion capabilities
Content sharing on social media platforms
Batch processing with up to 5 images per reel on Mobile
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
Only platform combining proprietary Spatial AI software with Switchable-Display hardware for immersive experiences on everyday devices
Enables immersive content without requiring new hardware—works on phones, tablets, laptops and monitors people already own
Portfolio of more than 2,000 patents—the largest in the industry—backing the technology
True holographic depth projection creating lifelike immersive effect without ghosting or visual artifacts
Content remains shareable across social media while maintaining immersive quality
Kokoro TTS
Immersity