Grok Voice 3.0SpaceXSI
|
Grok Voice AgentSpaceXSI
|
|||||
Related Products
|
||||||
About
Grok Voice 3.0 is a speech-to-speech model offered through the Grok Voice Agent API for developers building real-time voice applications. It accepts audio and text and returns spoken audio or text through a WebSocket session, supporting conversational turn-taking, interruptions, and function calling. Developers can connect the model to custom functions and server-side tools, including web search, X search, collections, and remote MCP servers. The API is intended for interactive voice agents such as customer-support and service-call experiences, and is also used for voice interactions in Tesla vehicles and Grok Bot. Billing is usage-based, with audio charged per minute and text input events billed separately. The API documentation includes setup instructions and examples for Python and JavaScript clients.
|
About
The Grok Voice Agent API is xAI’s new developer platform for building fast, intelligent, and multilingual voice agents. It is powered by the same in-house voice technology used by Grok Voice in mobile apps and Tesla vehicles. The API enables voice agents to speak dozens of languages, call tools, and search real-time data. Grok Voice Agents are engineered for low latency, delivering audio responses in under one second. The platform ranks first on the Big Bench Audio benchmark for voice reasoning performance. Developers benefit from a simple, flat pricing model based on connection time. The Grok Voice Agent API brings production-proven voice intelligence to custom applications.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Developers building real-time voice applications, phone agents, interactive voice systems, and customer-support experiences.
|
Audience
The Grok Voice Agent API is ideal for developers, startups, and enterprises building multilingual, real-time voice assistants for customer support, automotive, healthcare, finance, and conversational AI applications
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
$0.08/min
Audio is $0.08 per minute. Text-only input events are $0.004 each. Server-VAD sessions are billed for the full session duration; push-to-talk sessions are billed for audio sent and received.
Free Version
Not Supported
Free Trial
Supported
|
Pricing
$0.05 per minute
$0.05 per minute of connection time
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationSpaceXSI
Founded: 2023
United States
x.ai/api/voice
|
Company InformationSpaceXSI
Founded: 2023
United States
x.ai
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Grok
Supported
Grok Bot
Supported
Grok Voice 3.0
Not Supported
Grok Voice Agent
Supported
Grok Voice Agent Builder
Supported
Grok Voice Think Fast 1.0
Not Supported
Grok Voice Think Fast 2.0
Not Supported
Model Context Protocol (MCP)
Supported
Twilio
Supported
|
Integrations
Grok
Supported
Grok Bot
Not Supported
Grok Voice 3.0
Supported
Grok Voice Agent
Not Supported
Grok Voice Agent Builder
Not Supported
Grok Voice Think Fast 1.0
Supported
Grok Voice Think Fast 2.0
Supported
Model Context Protocol (MCP)
Not Supported
Twilio
Not Supported
|
|||||
|
|
|