Subvocal 眼镜将无声口述转换为每分钟 200+ 词的文本

AI 导读

Subvocal 推出可将无声口述转为文本的眼镜，转换速度达到每分钟 200+ 词。眼镜框架中的雷达捕捉面部与口部动作形成的反射变化，再由 AI 解码为文字，旁人至多只能看到轻微的嘴部动作。

正文 · 原文

I did not think this was possible yet. your face just became a keyboard.

Typing with no keyboard and no voice now exists, I’m still processing this launch.

Subvocal's glasses turn silently mouthed words into text at 200+ words per minute.

Voice dictation beats typing for speed, but it becomes unusable wherever talking aloud would disturb others or expose private text.

Now that problem is solved.

Underneath, radar travels from the frames through your face, each silently formed word changes how it reflects, and the AI decodes that into text at 200+ words per minute. The people around you see, at most, a little movement at your mouth.