jay-jlm

dspy-rag-fastapi

FastAPI wrapper around DSPy

wavesurfer.js

Audio waveform player

react-native-vision-camera

📸 A powerful, high-performance React Native Camera library.

fluent-env

A convenient wrapper around env-schema and fluent-json-schema.

voice-assistant-web

A smart voice assistant optimized for low latency responses.

cookbook

A resource of code examples, guides, and tutorials for using the AssemblyAI API.

openai-speech-to-text

chat-with-siri

🤖 A text-to-speech chatbot built using Nextjs, OpenAI, and ElevenLabs.

realtime-react-example

profanity-filter-demo

Submit a YouTube video and use AssemblyAI's Profanity Filter to censor profanities.

ai-voice-assistant-with-microsoft-azure-openai

extendable-media-recorder

An extendable drop-in replacement for the native MediaRecorder.

ai-jsx

The AI Application Framework for Javascript

modelfusion

The TypeScript library for building AI applications.

openai-whisper-api

A sample speech transcription app implementing OpenAI Text to Speech API based on Whisper, an automatic speech recognition (ASR) system, built using Next 13, the React framework

AlwaysReddy

AlwaysReddy is a LLM voice assistant that is always just a hotkey away.

hisanta.ai

Talk to Santa using Fixie Voice.

interrupting-cow

🐮📢 The first AI voice assistant that interrupts *you*

GPTPortal

A feature-rich portal to chat with GPT-4, Claude, Gemini, Mistral, & OpenAI Assistant APIs via a lightweight Node.js web app; supports customizable multimodality for voice, images, & files.

whisper-web

ML-powered speech recognition directly in your browser

telegram-chatgpt-concierge-bot

Interact with OpenAI's ChatGPT via Telegram and Voice.

assemblyai-node-sdk

The AssemblyAI JavaScript SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async and real-time transcription, audio intelligence models, as well as the latest LeMUR models.

react-vocal

React component and hook to initiate a SpeechRecognition session

MeloTTS

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

piper

A fast, local neural text to speech system

OAI-QuickChat

The quickest speech in speech out using the OpenAI and Elevenlabs APIs

Mage

Mage is a 3D Game Engine, built on top of THREE.js. It features Unity-like scripting, AMMO.js powered physics workers, an Infernojs powered UI and a clean API. Under (very) active development.

three-game-engine

Simple light-weight game engine using Three.js, three-mesh-ui, rapier.

three-nebula

WebGL based particle system engine for three.js

Bender

Bend Geometries in Threejs