Microsoft has introduced a highly practical new feature in its Edge browser: when users watch videos in English, the browser can leverage artificial intelligence to deliver real-time translation into their native language—for instance, Simplified Chinese—and output the result as audio. This allows viewers to continue watching without relying on subtitles.
Because the translation is processed locally by AI, the feature requires substantial system resources. According to Microsoft, only PCs equipped with at least 12 GB of RAM and a quad-core CPU can enable real-time video translation. Devices with lower specifications will not support this functionality.
The principle behind the feature is straightforward: the AI model first transcribes the video’s audio into text, then uses a text-to-speech model to generate translated audio. Since the entire operation is performed locally and in real time, it demands significant memory capacity.
The feature is already available in the Microsoft Edge Beta release. Users can upgrade to the Beta version, navigate to the language settings, and enable real-time video translation. Once activated, they can test the functionality with any video to see whether the translation works smoothly into their desired language.
The list of supported languages is extensive, covering virtually all major global languages. In terms of hardware, most PCs purchased in recent years come with at least 16 GB of RAM, while some older machines may still run on 8 GB.
For everyday office tasks, 8 GB of RAM remains serviceable. However, for gaming or AI-driven features, such as this one, 8 GB quickly proves insufficient. In such cases, upgrading to 32 GB or even 64 GB of RAM is strongly recommended, ensuring smoother performance for modern workloads and advanced AI functionalities.