Grok
Text-to-speech
Grok is xAI’s low-latency text-to-speech engine with a small set of multilingual voices.
Grok TTS does not take a model parameter. The voice string is just grok.<voiceId> —
never append a :model suffix.
Voices
Press play to audition any Grok voice, then copy config to grab the value for SWML or your SDK.
Grok provides five voices: ara, eve, leo, rex, and sal.
eve is the default, and is also used as the fallback when an unrecognized voice is requested.
See xAI’s documentation for voice details.
Languages
Grok voices are multilingual. SignalWire passes the language code you set on the
languages SWML method (any BCP-47 code, such as en-US
or fr-FR) to Grok, and multilingual mode maps to automatic language detection.
Usage
A voice identifier string has two parts: the grok engine code and a voice ID.
Format: grok.<voiceId>
voiceId(required): one of the voices above (for example,eve).
Examples:
Build with Grok on SignalWire
Create a Space and add credit
If you don’t have one yet, you’ll need to create a SignalWire Space. Be sure to add some credit to test with.
Add a new Resource
Navigate to the Resources tab in your SignalWire Dashboard and click + Add New to create a new Resource.
Create a SWML Script
From the Resources menu, select SWML Script. Name it something fun and recognizable. Ours is titled Grok Wizard.
Next, paste the following starter script into the text box, and hit Save:
Next steps with SWML
Now you’ve deployed your very first SignalWire voice AI application using Grok voices. Next, dive deeper into SWML to explore its capabilities!
