Microsoft’s AI Speech Generator Achieves Human Parity, Too Dangerous to Release

July 12th, 2024

Mmm hmm.

Meanwhile…

OpenAI’s new voice synthesizer can copy your voice from just 15 seconds of audio

From 2019: AI Clones Your Voice After Listening for 5 Seconds

From 2016: Adobe Voco:

Via: Techspot:

Microsoft has developed a new iteration of its neural codec language model, Vall-E, that surpasses previous efforts in terms of naturalness, speech robustness, and speaker similarity. It is the first of its kind to reach human parity in a pair of popular benchmarks, and is apparently so lifelike that Microsoft has no plans to grant access to the public.

Posted in Media, Perception Management, Rise of the Machines, Social Engineering, Technology | Top Of Page

One Response to “Microsoft’s AI Speech Generator Achieves Human Parity, Too Dangerous to Release”

  1. Snowman says:
    July 13, 2024 at 4:17 am

    First there was Hal. Now there’s Vall.

    Hal’s raison d’etre was that he could fly a spaceship. What is Vall’s?

Leave a Reply

You must be logged in to post a comment.