---
title: "AI Speech Generator ‘Reaches Human Parity’ — but It’s Too Dangerous To Release, Scientists Say"
metaTitle: "AI Speech Generator Too Dangerous to Release"
description: "Microsoft has developed VALL-E 2, an AI voice cloning technology it claims is so dangerously realistic that the company has elected not to make it public."
slug: ai-speech-generator-too-dangerous-to-release
date: "2024-07-10T12:00:00-05:00"
image:
  src: "https://cdn.securelogix.dev/slx/images/ai-speech-generator-reaches-human-parity.webp"
  alt: "A woman appears to investigate her reflection, but its asymmetry with her reveals that it is a clone."
sourcePublisher:
  name: Live Science
  url: www.livescience.com
sourceArticle:
  url: "https://www.livescience.com/technology/artificial-intelligence/ai-speech-generator-reaches-human-parity-but-its-too-dangerous-to-release-scientists-say"
tags: [AI, Deepfake, Vishing]
status: published
---

## Microsoft’s VALL-E 2 can convincingly recreate human voices using just a few seconds of audio, its creators claim.

Microsoft has developed a new artificial intelligence (AI) speech generator that is apparently so convincing it cannot be released to the public.

VALL-E 2 is a text-to-speech (TTS) generator that can reproduce the voice of a human speaker using just a few seconds of audio.

Microsoft researchers said VALL-E 2 was capable of generating “accurate, natural speech in the exact voice of the original speaker, comparable to human performance,” in a paper that appeared June 17 on the pre-print server arXiv. In other words, the new AI voice generator is convincing enough to be mistaken for a real person — at least, according to its creators...