Lightning-Fast, On-Device TTS — running natively via ONNX.

Text to Speech (TTS) addon for qvac (ggml backend, wrapping the chatterbox + supertonic + parler engines from tts-cpp)

A standalone TypeScript library for Supertonic TTS using ONNX runtime.

React Native wrapper for sherpa-onnx offline TTS — Supertonic 3 text-to-speech engine for Android (31 languages)

On-device text-to-speech CLI for AI agents (Supertonic-3, ONNX).

TypeScript bindings for the Supertonic TTS Tauri plugin

Browser-based voice AI: **Whisper** (Transformers.js) for speech-to-text, **Kokoro** and **Supertonic** (ONNX) for text-to-speech, plus **Web Speech API** and **external HTTP** providers. Includes an embeddable **`<voice-chatbot>`** with a queued TTS pipe

voice-connect — voice service for agents. MCP tools tts (text → ready-to-send .ogg/opus voice file) and stt (audio → text) over one core, plus an OpenAI-compatible HTTP facade (/v1/audio/speech + /v1/audio/transcriptions) for runtimes. Cascade with fallba

A high-performance React Native library for text-to-speech on iOS and Android

Official model catalogs and metadata for polytts.

ONNX Runtime Plugin for Unity

ONNX Runtime Utilities for Unity

ONNX Runtime Extensions for Unity

Add-on — read-only screen perception (structured UIA tree + pixel fallback + noise-filtered background watch with an event buffer + sub-second reflex alerts: beep / fixed-phrase / OCR or optional local-VLM description spoken locally, optional higher-quali

Run small open AI models entirely in the browser with WebGPU: model catalog, capability slots, WebLLM + Transformers.js + Kokoro inference, streaming, schema-constrained JSON, metrics, cache management, and a press-to-talk voice pipeline — as an embeddabl

Music theory library for generating and working with chords, modes, intervals, etc.

Core runtime and adapter contracts for polytts.

Node entrypoint for polytts text-to-speech runtimes.

Voice shopping widget — drop-in JS for Shopify, WooCommerce, Odoo and custom stores

On-device neural TTS for React Native and Expo. Multi-engine, sub-second TTFA, 31 languages, fully offline.