OpenAI, which is behind ChatGPT, has come up with a voice cloning AI model that only needs a 15-second sample to work.

Voice Engine is an expansion of the company’s existing text-to-speech API. It allows users to upload any 15-second voice sample to generate a synthetic copy of that voice. But there’s no date for public availability yet.

“These small-scale deployments are helping to inform our approach, safeguards, and thinking about how Voice Engine could be used for good across various industries,” OpenAI said in its blog post.

Companies that have access include the education technology company Age of Learning, visual storytelling platform HeyGen, frontline health software maker Dimagi, AI communication app creator Livox, and health system Lifespan, according to The Verge. The technology may have huge implications for those who record themselves speaking often, like podcasters, voice-over artists and spoken word performers.