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

robot
Abstract generation in progress

According to Beating Monitoring, xAI has launched Grok Custom Voices and the Voice Library. Users can record a voice clip in the xAI console to generate their own voice_id, then integrate it with the Grok TTS or Voice Agent API for scenarios such as customer service agents, content creation, game characters, audiobook narration, and more.

This set of features is not as simple as uploading audio to clone someone’s voice. Users must read a short verification phrase aloud. The system will use STT for real-time transcription, and then compare the speaker characteristics between the verification recording and the full recording; only after confirming it is the same person will it generate the voice profile. xAI says this can prevent cloning other people’s voices using existing recordings.

Currently, Custom Voices are available only in the United States, excluding Illinois. Up to 30 custom voices can be created for free in the console. API creation capability is available only to Enterprise teams. Custom voices themselves are not charged separately, but calls to the voice API are billed by usage: Realtime at $3.00/hour, and 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