Advertisement
OpenAI has introduced a groundbreaking tool called Voice Engine, capable of replicating a person’s voice with just a 15-second audio clip.
This innovative model, Voice Engine, analyzes a brief 15-second recording to grasp the nuances of the individual’s voice and speech patterns. Subsequently, users can input text, and the tool synthesizes the desired speech with remarkably realistic voices, complete with emotional nuances. While OpenAI initially developed Voice Engine in 2022 for preset voices, this marks the first time the company has discussed its application using an individual’s authentic voice. However, OpenAI also acknowledges the significant potential for misuse and malicious intent associated with such technology.
In a blog post released on Friday (March 29), OpenAI emphasizes its cautious and informed approach towards a broader release of Voice Engine, recognizing the grave implications of synthetic voice misuse. The company aims to initiate a dialogue on the responsible utilization of synthetic voices and the necessary societal adaptations to accommodate these new capabilities.
“We are taking a cautious and informed approach to a broader release due to the potential for synthetic voice misuse,” OpenAI wrote in a blog post. “We hope to start a dialogue on the responsible deployment of synthetic voices, and how society can adapt to these new capabilities.”
OpenAI underscores the importance of gathering feedback from various stakeholders, including governments, media companies, entertainment companies, and educational institutions, both domestically and internationally. These entities are currently testing Voice Engine and have agreed to refrain from impersonating others. Moreover, they are mandated to disclose to listeners that the voice they are hearing is AI-generated. OpenAI has also implemented watermarking to signal that the voice is synthetic, not authentic.
“We believe that any broad deployment of synthetic voice technology should be accompanied by voice authentication experiences that verify that the original speaker is knowingly adding their voice to the service and a no-go voice list that detects and prevents the creation of voices that are too similar to prominent figures,” the company said.
Looking towards the future, OpenAI remains uncertain about the fate of Voice Engine. While there is a possibility of eventual public release, the company may also determine that such a move is not in the best interest of the public. Regardless, OpenAI stresses the importance of global awareness regarding the trajectory of this technology, emphasizing the need for informed discussion and understanding of its potential implications.
“It’s important that people around the world understand where this technology is headed,” the company said, “Whether we ultimately deploy it widely ourselves or not.”