Google在Gemini Live中推出了Guided Vision功能，利用人工智能为兼容的Android设备用户提供实时音频描述1。用户可以通过Gemini Live共享相机画面，获得AI的即时语音反馈1。
该功能的应用包括读取小字体文本、描述周围环境、查找和识别物体以及详细描述特定物体的细节1。Guided Vision主要面向盲人、低视力人群或在特定场景中需要视觉辅助的用户1。这一功能与Apple在iPhone和Vision Pro上已支持的VoiceOver Live Recognition功能相似1。
Google has introduced Guided Vision, a new accessibility feature within Gemini Live that uses artificial intelligence to provide real-time audio descriptions for Android device users.1 The feature enables users to share their camera feed with Gemini Live and receive AI-generated narration to assist with reading small text, describing surrounding environments, identifying objects, and providing details about specific items.1
The Guided Vision feature is designed primarily for blind individuals, those with low vision, and users who require situational assistance.1 By leveraging the camera capabilities of compatible Android devices, the feature offers accessible support for navigating visual information in everyday scenarios.1 This functionality is comparable to similar tools, such as Apple's VoiceOver Live Recognition, which is currently available on iPhone and Vision Pro devices.1
评论
还没有评论，欢迎留下第一条。