Sign in
← AI PulseAug 20, 2026

Wire · news · Multi-source brief

xAI Introduces Custom Voice Cloning for Text-to-Speech and Speech-to-Speech APIs

xAI has launched a new Custom Voices feature, allowing users to clone a voice from a short audio clip for use across its Text to Speech and Speech to Speech APIs.

By Illumora Editorial

Source · Aug 20, 2026, 3:13 PM · On Illumora · Aug 20, 2026, 3:58 PM

Media from the primary source — shown here so you can stay on Illumora.

Synthesized from multiple allowlisted primaries on the same event. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →xAI Docs — Custom Voices | SpaceXAI Docs
Save

xAI has introduced Custom Voices, a new feature that enables users to clone a voice from an audio clip. This cloned voice can then be applied across the xAI Text to Speech and Speech to Speech APIs. The feature is currently available in the United States, with the exception of Illinois.

Key Points

  • Users can clone a voice from a short reference clip and use it with xAI's TTS and Speech to Speech APIs.
  • Custom voices are interchangeable with built-in voices across all voice APIs.
  • A reference audio clip of up to 120 seconds can be used for cloning, with 90–120 seconds recommended for optimal results.
  • The system captures both the timbre and delivery patterns from the reference clip.
  • Users can create up to 30 custom voices for free via the console.
  • API access for creating custom voices is gated to teams on an Enterprise plan.
  • Custom voices are scoped to the user's team and are not available to other users.

Context

According to xAI, the Custom Voices feature allows for personalized speech synthesis by replicating a speaker's unique vocal characteristics. The company emphasizes that the quality of the cloned voice depends on the reference audio, recommending a quiet recording environment with a high-quality microphone and expressive, natural speech. For Enterprise users, the voice_id is returned directly in the API response when a custom voice is created.

Why It Matters

This feature offers developers and content creators the ability to generate highly personalized audio content, potentially enhancing user experience and brand consistency by using specific voices for various applications. The ability to clone voices for free in the console also lowers the barrier to experimentation for individual users.

What To Do

  • Check the xAI Docs for detailed instructions on using the Custom Voices feature.
  • Experiment with different reference clip lengths, aiming for 90–120 seconds, to observe the impact on voice quality.
  • Note the recommendations for recording environment and microphone quality to achieve optimal results.
  • For Enterprise users, explore the API for programmatic creation and management of custom voices.

Keep Exploring

/atlas/**grok**-family /techniques/multimodal-grounding