AI Explorer
AI Explorer
Apr 3, 2026 · Artificial Intelligence

VibeVoice: Open‑Source Real‑Time TTS and 60‑Minute ASR from Microsoft

VibeVoice is a Microsoft‑backed open‑source framework that combines streaming text‑to‑speech and ultra‑long audio speech‑to‑text capabilities, offering multilingual models, low‑latency generation, speaker diarization, and easy deployment via Hugging Face, positioning it as a commercial‑grade alternative for developers.

Hugging FaceMicrosoftlong-form ASR
0 likes · 7 min read
VibeVoice: Open‑Source Real‑Time TTS and 60‑Minute ASR from Microsoft