xAI launches the Custom Voices feature, allowing users to clone a voice by recording 1 minute of speech

robot
Abstract generation in progress

AIMPACT News, May 4th (UTC+8), xAI launched the “Custom Voices” feature, allowing users to clone their own voice by recording approximately 1 minute of speech. The voice model can be prepared within 2 minutes and integrated with xAI’s text-to-speech and voice proxy APIs. To prevent abuse, the system employs a two-step verification process: users first read a real-time check phrase, then confirm their identity through voice feature comparison, preventing cloning of others or existing recordings. The xAI console also launched the “Voice Library” feature, offering over 80 pre-installed voices covering 28 languages, with no charge for using cloned voices. This feature is built on Grok’s speech-to-text and text-to-speech APIs, as well as the “Grok Voice Think Fast 1.0” voice proxy model, and has provided technical support for Starlink customers’ support and sales.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin