microsoft/VibeVoice
Open-Source Frontier Voice AI
- Stars56.4k
- LanguagePython
- LicenseMIT
Open-Source Frontier Voice AI
Open-Source Frontier Voice AI
2026-09-03: 🚀 We released VibeVoice-ASR-Streaming, a unified streaming ASR model that continuously transcribes ''who said what'' as speech arrives, with support for customized hotwords and 10 languages. [Demo] [Models] [Report]
2026-07-23: ⚡ We released VibeVoice-ASR-BitNet, an edge CPU inference engine for VibeVoice-ASR. Through heterogeneous quantization (I8_S + I2_S), the model is compressed from 4.62 GB to 1.58 GB with real-time inference (RTF Code] [Models] [Report]
Description and README excerpt from microsoft/VibeVoice on GitHub ↗.
microsoft/VibeVoice was first seen on GitHub · Trending today on Nov 5, 2026. Since then it has appeared in 48 checks on 4 different days, across 2 lists (GitHub · Trending today, GitHub · Trending Python today). Its best position was #12 of 14, reached on Nov 6, 01:32 UTC. It dropped off the list after Nov 8, 10:55 UTC.
Position on GitHub · Trending today at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by GitHub.
| List | Best | Days | Checks | Last seen |
|---|---|---|---|---|
| GitHub · Trending today | #12 | 2 | 24 | |
| GitHub · Trending Python today | #5 | 4 | 24 |
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 8, 10:55 UTC, after 4 days of trending.
#12 on GitHub · Trending today, on Nov 6, 01:32 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 5, 2026 and has been on the list on 4 days (48 checks) since.
Mostly Python; it is licensed under MIT. It has 56.4k stars and 6348 forks.