A Javascript library for running ONNX models on browsers

HeadTTS: A free Javascript text-to-speech with timestamps and visemes.

A Javascript library for running ONNX models on browsers

GGML-backed OCR addon for qvac (EasyOCR pipeline on GGUF weights)

High-quality text-to-speech for the web

Node-first OCR interface with support for Tesseract.js, ONNX (PaddleOCR), HappyVertical AI-backed vision OCR, and Unlimited-OCR

Fractal memory system for OpenCode with semantic search and automatic compression.

Portable local/remote embedder for @plurnk/plurnk-mimetypes' explicitly requested embedding seam. The bundled local MiniLM path uses vendored WASM with no native addon, runtime network, or transitive install scripts.

Fork of @diffusion-studio/vits-web for easier built-in PiperTTS use.

Mailwoman neural-classifier weights for locale 'fr-fr'. Data-only overlay — shares the base model.onnx + tokenizer.model from @mailwoman/neural-weights-en-us (they are byte-identical); ships only the fr-specific data siblings. Loaded by @mailwoman/neural

A cross-platform OCR library based on PaddleOCR v5 and ONNX Runtime that is as small as possible.

ONNX Runtime detection backend for camera.ui. Runs object detection, face detection and recognition, license plate recognition with OCR, and CLIP semantic embeddings.

edgevox-onnx 1.13.4 with native Windows x64 and Android TTS, portable WASM fallback, ZipVoice, Chatterbox Turbo, and Wfloat emotional TTS.

MediaPipe face landmark detection neural network model for Unity Barracuda

ONNX Runtime backend for RunAnywhere React Native SDK - Speech-to-Text, Text-to-Speech, and VAD

Mailwoman neural-classifier weights for locale 'en-us'. Data-only package — loaded by @mailwoman/neural at runtime.

MediaPipe hand landmark detection neural network model for Unity Barracuda

MediaPipe face landmark detection neural network model for Unity Barracuda

MediaPipe iris landmark detection neural network model for Unity Barracuda

Web api for using VITS based models in the browser!