Unverified50% confidenceReleaseExact time
微软开源了流式语音识别模型VibeVoice系列，可在接收音频输入的同时实时转录文本并自动标注说话人
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
Unverified微软的VALL-E及开源项目Bark和RVC等语音克隆技术能仅凭数秒语音样本生成高度逼真的仿声音频75% similarUnverifiedIn Windows voice input online mode, voice data is sent to Microsoft's cloud for processing, yielding higher recognition accuracy; offline mode processes locally with lower latency74% similarUnverified谷歌NotebookLM的Audio Overview功能允许用户上传文档后自动生成两位AI主持人进行深度讨论的播客音频73% similarUnverified剪映具有自带的语音识别功能，可以将直播录像中的语音转化为字幕文本73% similarUnverifiedGoogle 的 AudioPaLM 是直接实现音频到音频映射的端到端语音模型73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893015API
curl https://kongchang.com/api/v1/knowledge/claims/893015MCP
get_claim(id=893015)