AI Audio2025
Runs text-to-speech with instant voice cloning fully on-device, from phones to GPUs. Built on small LLM backbones (120M-360M params) plus a 50Hz neural codec; clones a voice from ~3 seconds of audio across English, Spanish, German, and French.
AI Model2025
Turns clinical text into structured, de-identified clinical signals—entity extraction and PII de-identification—that run entirely on local hardware. Provides 1,000+ specialized medical NER models, multilingual support, Apple MLX acceleration, and Apache‑2.0 licensing.
Embodied AI2025
Detects motion from Wi‑Fi channel state information (CSI) on cheap ESP32 boards and integrates natively with Home Assistant; offers an optional on‑device ML detector that requires no calibration.
Embodied AI2025
Contains training, evaluation, and deployment code plus checkpoints for humanoid whole-body controllers (Decoupled WBC and GEAR‑SONIC). Includes C++ inference, VR teleoperation, data pipelines (Bones‑SEED) and Hugging Face checkpoints for research-to-robot workflows.
AI Audio2025
Delivers multilingual, on-device text-to-speech via ONNX Runtime with prebuilt ONNX assets and cross-platform SDKs (Python, Node, mobile); targets low-latency, privacy-preserving TTS with ready demos and 31-language support in v3.
AI Infra2025
Combines a vector store, Cypher-style graph queries, and on-device LLM inference in one Rust engine, with a graph neural network that reranks results and adapts to query patterns in under a millisecond. Services ship as self-contained .rvf containers.
AI Video2025
Runs text-to-video, image-to-video, text-to-image, and image editing inference with acceleration, offloading, quantization, and distributed execution for large visual generation models.
AI Video2025
Generates real-time, infinite-length portrait video from one reference image on a 12GB GPU. Combines implicit facial signals and 3D keypoints with step-distilled diffusion and autoregressive micro-chunk streaming for low-latency live use.
AI Model2025
Converts images (and other conditions) into high-fidelity, fully textured 3D assets using a 4B-parameter generative model and a field‑free sparse voxel format (O‑Voxel). Handles arbitrary topology, PBR materials, and near real-time mesh/voxel conversions; requires Linux and an NVIDIA GPU with >=24GB memory.
AI Client2025
Provides a plug-and-play inference engine that lets language models programmatically inspect, decompose, and recursively call themselves to handle very long contexts; supports local and cloud REPL sandboxes, multiple LLM backends, and trajectory logging/visualization.
AI Video2026
Provides a DiT-based audio–video foundation model plus an official Python inference and LoRA trainer. Ships multiple production-ready pipelines (text/image/audio→video), checkpoints, and performance optimizations (FP8, distilled pipelines) for high-fidelity synchronized audio–video generation.
AI Deploy2026
Enables parallel speculative decoding by using a lightweight block-diffusion draft model to produce multi-token drafts for faster, high-quality generation. Integrates with vLLM, SGLang and Transformers backends and ships draft models on Hugging Face.