Real-time system audio translation for macOS — translate any audio (YouTube, podcasts, meetings) live on screen with OpenAI or Google Gemini. On-device speech recognition; optional low-latency realtime mode.

ACL 2026 Demo: Real-time bidirectional Korean-English speech translation over PSTN telephone calls. Server-side relay with dual-session echo gating. 555ms median latency, USD 0.28/min.

A Powerful Real-Time Chat Platform that breaks language barriers by automatically translating messages between users in different languages. Built using modern web technologies, this application enables seamless global communication with built-in voice accessibility for inclusive and user-friendly interaction.

Real‑time voice translation with offline/online ASR & multi‑backend translation.

🎙 Realtime multilingual voice translation with live captions, group rooms, FFT waveform & subtitle-style UI — Qwen3-ASR + DeepSeek + OpenAI Realtime, FastAPI + Vanilla JS

OpenAI Realtime Translation PoC for YouTube live translation with WebRTC, Chrome tab audio, and Korean captions

A beginner-friendly Python prototype for real-time speech and text translation, using Hugging Face translation models, Google Speech Recognition, and text-to-speech demos.

Realtime speech transcription and translation plugin for macOS IINA