OpenAI has unveiled a voice-cloning technology that can replicate a person’s voice with just 15 seconds of audio input.
What Happened: OpenAI, a company backed by Microsoft Corp MSFT, has introduced a voice-cloning technology that requires only 15 seconds of audio material to imitate a person’s voice, OpenAI revealed in its blog post. The technology, known as Voice Engine, can produce “emotive and realistic” speech that closely resembles the original speaker.
OpenAI has emphasized the need for a “cautious and informed approach to a broader release due to the potential for synthetic voice misuse.” The company is seeking to initiate a discussion on the responsible deployment of synthetic voices and how society can adapt to these new capabilities.
The technology has raised concerns about potential misuse, including voice cloning for fraudulent activities and its impact on the livelihoods of voice actors. However, OpenAI also highlights positive applications, such as providing reading assistance to non-readers and children, instant translation of videos and podcasts, and helping patients who are losing their voice through illness to continue communicating using what sounds like their own voice.
See Also: Microsoft, OpenAI Reportedly Plan $100B Supercomputer Project ‘Stargate’
Why It Matters: The rapid advancement of AI voice-cloning technology has raised ethical and practical concerns. OpenAI’s Voice Engine, which requires just 15 seconds of audio, represents a significant leap in this field. This development could have far-reaching implications for various industries, including entertainment, security, and healthcare.
Earlier this year, OpenAI’s Sora, a text-to-video generator, impressed many, but the company stated that it’s still in the early testing phase. In a bid to replicate OpenAI’s text-to-video generator, Peking University has joined forces with RabbitPre, an AI company based in Shenzhen, China.
AI voice technology is also revolutionizing other industries. Adobe Research, a division of Adobe, has announced a new experimental tool, Project Music GenAI Control, that leverages generative AI to revolutionize the creation and editing of custom audio and music.
Image Via Shutterstock
Engineered by Benzinga Neuro, Edited by
Kaustubh Bagalkote
The GPT-4-based Benzinga Neuro content generation system exploits the extensive Benzinga Ecosystem, including native data, APIs, and more to create comprehensive and timely stories for you.
Learn more.