Clones voices from audio samples and generates steerable speech in 43 languages. Its sparse MoE activates about 100 million parameters per token, enabling real-time use in browsers and on local devices.
Combines text-to-image generation and reference-guided editing in one model, producing images around 16 megapixels and accepting up to 16 reference images.
Runs a 145B agent model on a single consumer GPU using sparse latent MoE. The NVFP4 build reports 98.3 tok/s agent decoding on an RTX 5090 D, while also relying on host RAM.
Processes incoming and outgoing speech in parallel for real-time conversation, producing synchronized audio and text at 7.5 frames per second. Its continuous-audio design targets natural turn-taking rather than a conventional voice-assistant workflow.