xAI API launches voice cloning feature

robot
Abstract generation in progress

AIMPACT News, May 2 (UTC+8), xAI recently launched a voice cloning feature through the xAI API. Users can record approximately one minute of natural speech in the console, and the system completes voice ownership verification and recording processing within two minutes to generate a production-level voice model. The cloned voice supports voice tagging, multilingual output, and streaming via REST and WebSocket, and can be used just like all built-in voices (over 80 types, covering 28 languages). For security, a two-phase verification process is employed: first, real-time transcription matching of a read phrase for verification, then speaker embeddings are calculated from the verification segment and the full recording to confirm identity. Users cannot clone voices from existing recordings nor clone others’ voices. Using custom voice TTS or speech proxy APIs incurs no additional charge. (Source: InFoQ)

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