微软 VibeVoice-Realtime-0.5B
Real-time TTS with 300ms latency, real-time on RTX 4090 — on-device real-time speech
No direct GitHub link yet — star count pending verification before we write it up.
Real-time TTS with 300ms latency, runnable in real time on an RTX 4090 — on-device real-time speech.
Voice AI: lifelike TTS, accurate ASR, and real-time voice agents.