Grok launches voice cloning: record one minute, and you can create your own AI voice profile

robot
Abstract generation in progress

CryptoWorld News reports that Grok has launched a voice cloning feature, allowing users to generate their own AI voice by recording just one minute of audio. This feature enables users to record their voice on the xai console, generate a voice_id, and connect to Grok’s TTS or voice agent API, suitable for customer service, content creation, game characters, and audiobook narration scenarios. Users need to read a verification phrase aloud, and the system performs real-time transcription via STT and compares voice features to confirm the speaker before generating the voice, preventing others’ voices from being cloned. Currently, the custom voices feature is only available in the United States, excluding Illinois. The console allows up to 30 free custom voices, and API creation capabilities are only available to enterprise teams. Custom voices are free of charge, but API usage is billed per use: real-time at $3.00/hour, text-to-speech at $4.20 per million characters.

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