OpenAI rolls out ‘Voice Engine’ to recreate human voices

By Shilpa Annie Joseph, Official Reporter
  • Follow author on
OpenAI launches Voice Engine
Rep. image | Courtesy: Levart_Photographer @ Unsplash

OpenAI, the US-based artificial intelligence research organization, has unveiled technology that can recreate someone’s voice.

Voice Engine uses text input and a single 15-second audio sample to generate natural-sounding speech that closely resembles the original speaker. The company said that “a small model with a single 15-second sample can create emotive and realistic voices.”

OpenAI first developed Voice Engine in late 2022 and has used it to power the preset voices available in the text-to-speech API as well as ChatGPT Voice and Read Aloud. To better understand the potential uses of this technology, late last year the company started privately testing it with a small group of trusted partners.

The new technology will provide reading assistance to non-readers and children through natural-sounding, emotive voices representing a wider range of speakers than what’s possible with preset voices.

According to the statement, “Age of Learning, an education technology company dedicated to the academic success of children, has been using this to generate pre-scripted voice-over content. They also use Voice Engine and GPT-4 to create real-time, personalized responses to interact with students. With this technology, the Age of Learning has been able to create more content for a wider audience.”

Further, It will translate content, like videos and podcasts, so creators and businesses can reach more people around the world, fluently and in their own voices.

One early adopter of this is HeyGen, an AI visual storytelling platform that works with their enterprise customers to create custom, human-like avatars for a variety of content, from product marketing to sales demos. They use Voice Engine for video translation, so they can translate a speaker’s voice into multiple languages and reach a global audience.

“When used for translation, Voice Engine preserves the native accent of the original speaker: for example generating English with an audio sample from a French speaker would produce speech with a French accent,” the company noted.

Voice Engine is a continuation of OenAI’s commitment to understanding the technical frontier and openly sharing what is becoming possible with AI. It also intends to help patients recover their voice, for those suffering from sudden or degenerative speech conditions.

Trending | unveils breakthrough AI WhatsApp Bot service