xAI has launched a new feature called Custom Voices, allowing users to clone a voice from a short audio recording and use it in its Text-to-Speech (TTS) and Voice Agent APIs.
According to xAI, users can record about a minute of natural speech through the xAI console.
The system verifies the speaker’s identity using a passphrase check and voice matching before generating a custom voice model.
The company says the process takes under two minutes and produces a ready-to-use voice.
The custom voices can be used across supported TTS features, including real-time voice agents. They also support multiple languages, speech tags, and both REST and WebSocket streaming.
On the other hand, xAI also introduced a Voice Library, a console-based tool that lets teams browse, preview, and manage both built-in and custom voices in one place.
The library currently includes over 80 built-in voices across 28 languages.
Additionally, xAI said that voices cannot be cloned from existing recordings and are restricted to the verified speaker only.
For its availability, xAI confirmed that there will be no additional charges applied for using custom voices on Grok.
ManilaShaker is a tech media producing insightful and helpful content for our local and growing international audience. Our goal is to create a premier Philippine digital consumer electronics resource that provides the most objective reviews and comparisons globally.
