Event ·Multi-source

智谱AI发布GLM-4.5V，支持语音输入并逐步生成文本

智谱AI的GLM-4.5V模型通过官网中文“环境问题”样例验证，能随着录音播放逐步生成文本。测试重点包括已提交文字是否会回改以及遇到停顿时如何继续提交。

Current read

智谱AI新出的GLM-4.5V模型现在支持语音输入了，你可以对着它说话，它会一步步生成文字，比之前版本更方便。

10 sources37° AI heatLast updated 2026/9/16 13:10:05

Evidence

10 sources

Primary sourceshao__meng

2026/9/16 13:10:05View source

Related source 1小互

2026/9/17 02:10:49View source

Related source 2量子位

2026/9/15 12:47:16View source

Related source 3Harrison Chase

2026/9/15 13:50:43View source

Related source 4Genk

2026/9/16 15:24:00View source

Related source 5Fireworks AI

2026/9/16 22:09:49View source

Related source 6pandaily

2026/9/18 07:51:45View source

Related source 7Mustafa Suleyman

2026/9/15 14:45:45View source

Related source 8Tech in Asia

2026/9/17 00:50:24View source

Related source 9Yangyi

2026/9/18 10:44:26View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story