[ad_1]
Microsoft has a new AI toy — and no, you can’t use it.
The company’s researchers revealed in a research paper (spotted by Live Science) that they built an AI speech synthesizer capable of creating believable and realistic human voices directly from text prompts.
Called VALL-E 2, the research paper claims it is the first time “human parity” has been achieved in a text-to-speech system.
Speed of Light Mashable
The best Windows laptops of 2024: Add these models to your Prime Day shopping list
Of course, there is no way for any of us to know for sure, because ordinary people can’t use it. Microsoft Blog Post is very clear on this.
“This page is intended for research demonstration purposes only,” Microsoft’s website states. “We currently have no plans to integrate VALL-E 2 into a product or broaden public access.”
Unfortunately, there are no audio samples available, so you’ll have to trust the researchers on this one. However, the blog post does offer plenty of graphs and technical terms to explore. But if it’s as good as they say it is, maybe it’s for the best that we can’t hear it.
The subjects
Microsoft Artificial Intelligence