microsoft/VibeVoice Resurges on GitHub Trending at 24,452 Stars — Open-Source TTS + ASR Covering 50+ Languages

GitHub·medium signal

Microsoft's open-source voice AI family is back on GitHub trending at +320 stars/day. VibeVoice-ASR handles 60-minute long-form audio in a single pass with speaker diarization (who/when/what), supporting 50+ languages. The TTS side generates expressive multi-speaker conversational audio like podcasts. Core innovation is continuous speech tokenizers at ultra-low 7.5 Hz frame rate — preserving fidelity while boosting efficiency for long sequences. Realtime-0.5B model supports streaming text input.