We recently shared a preview of a model called Voice Engine, which uses text input and a single 15-second audio sample to generate natural-sounding speech that closely resembles the original speaker.

We recognize that generating speech that resembles people's voices has serious risks, and we are taking a cautious approach to a broader release due to the potential for synthetic voice misuse. We are engaging in discussions and small scale tests with U.S. and international partners to ensure we are incorporating their feedback as we build.

At this time, we are choosing to preview but not widely release this technology. Based on the results of our small scale tests, we will make a more informed decision about whether and how to deploy this technology at scale.