Microsoft's open-source VibeVoice hits 56.5k stars, generates hours-long multi-speaker speech
solyarisoftware · x · 2026-11-07
Microsoft's VibeVoice is an open-source (MIT) frontier voice AI project with 56.5k GitHub stars that generates long-form, multi-speaker speech — suitable for podcasts, audiobooks and voiceovers without ever touching a microphone.
Recent releases:
- VibeVoice-ASR-Streaming: streaming ASR that transcribes "who said what" in real time, with custom hotwords and 10 languages
- VibeVoice-ASR-BitNet: edge CPU inference engine, compressing the ASR model from 4.62GB to 1.58GB with real-time inference (RTF < 1) on 3+ CPU threads, no GPU needed
More from Multimodal
- Midjourney 8.2 test: stunning Munch-inspired expressionist artwork — LudovicCreator · 2026-11-07
- Midjourney style code --sref 4173596805: cinematic grainy night scenes of the Colosseum — sergeantsref · 2026-11-07
- How I built a rhythm racing game with Claude Opus 5.5, six skills, and a voice feedback loop — Groowl · 2026-11-07
- Stylized 2D-to-3D character conversion preserves every design detail — azed_ai · 2026-11-07
- Doki lets you make videos with no timeline — just write the whole thing as one story — thesephist · 2026-11-07
- hyperflow-h3-flash video model updated: sampling in just 4, 6, or 8 steps — Apprehensive_Sky892 · 2026-11-07