xAI's new Custom Voices feature turns a minute of speech into a usable voice clone
xAI has launched a new feature called "Custom Voices" that lets users clone their own voice with just a short recording. All it takes is about a minute of natural speech captured through the xAI console. xAI says the voice model is ready in under two minutes and can be plugged into the company's text-to-speech and voice agent APIs.
To prevent misuse, xAI uses a two-step verification process. Users first read a passphrase that's checked in real time, and the system then compares the voice characteristics of both recordings to confirm the same person is speaking. According to xAI, the setup makes it impossible to clone existing recordings or someone else's voice.
The xAI console also gets a new "Voice Library" with more than 80 preinstalled voices across 28 languages. Using cloned voices doesn't cost extra.
"Custom Voices" builds on xAI's recently launched Grok Speech-to-Text and Text-to-Speech APIs and the "Grok Voice Think Fast 1.0" voice agent model, which xAI says already powers Starlink's customer support and sales.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe nowRead on for the full picture.
Subscribe for hype-free coverage.
- Full access to every article on THE DECODER
- No ads
- Join the comments and community discussions
- A weekly AI news recap via mail
- 6x/year: "AI Radar" — deep dives on the AI topics that matter most
- Daily AI news, always up to date
- Our full ten-year archive
- Covered by a team with 10+ years in AI