websocket

Server & client for DeepSpeech using WebSockets for real-time speech recognition in separate environments

Local-first meeting transcription — audio & transcripts never leave your machine. Live captions + upload diarization + voice matching.

Sample Unity project used to demonstrate Speech Recognition using the new Microsoft Speech Service (Preview) via WebSockets.

TikTok LIVE API Client ‣ Real-time AI STT, chat, gifts, viewers, battles & events from any TikTok livestream. Managed WebSocket with 99.9% uptime. Node.js, Python, Java, Go, C#.

Open-source AI assistant with voice control, browser automation, desktop overlay, and 109+ tools. Built with Python, Next.js, and Three.js.

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

Practice real voice interviews with an AI interviewer, get coding problems evaluated live, and receive a scored performance report.

React/Next.js visual dashboard for the OpenClaw AI gateway — every CLI command as a UI page, with speech-to-text everywhere

Experimental web console for real-time multimodal AI interactions (voice/video) using Gemini 2.0 Live API and NijiVoice. Next.js (TypeScript, Tailwind) frontend and FastAPI backend communicate over WebSocket for low-latency streaming.