Introducing the Voice Agent Builder | xAI

Back to newsJul 1, 2026<br>Introducing the Voice Agent Builder

Create a personalized voice agent in under 2 minutes without a single line of code.

[data-slot=icon]]:-mx-0.5 [&>[data-slot=icon]]:shrink-0 gap-x-2 px-3.5 py-1.5 sm:text-sm [&>[data-slot=icon]]:size-4 [&>[data-slot=icon]]:sm:size-3 bg-[--btn-bg] text-[--btn-text] hover:brightness-90 rounded-full [--btn-bg:theme(colors.primary)] [--btn-border:theme(colors.primary)] [--btn-hover:theme(colors.nimbus)] [--btn-text:theme(colors.background)]" href="https://console.x.ai/team/default/voice/agents?campaign=agent-builder-blog&builder=1">Try It Free<br>[data-slot=icon]]:-mx-0.5 [&>[data-slot=icon]]:shrink-0 gap-x-2 px-3.5 py-1.5 sm:text-sm [&>[data-slot=icon]]:size-4 [&>[data-slot=icon]]:sm:size-3 bg-[--btn-bg] text-[--btn-text] ring-1 ring-[--btn-border] hover:bg-[--btn-hover] rounded-full [--btn-bg:transparent] [--btn-border:theme(colors.primary/15%)] [--btn-hover:theme(colors.primary/5%)] [--btn-text:theme(colors.primary)]" href="/voice">Explore Voice Agents

Today, we’re announcing Voice Agent Builder in beta: a no-code platform to configure production voice agents on Grok Voice.

It’s for operators and developers who want high-volume production voice agents without building the surrounding stack from scratch. Out of the box you get telephony, knowledge retrieval, tools, guardrails, MCPs, and observability in one place. You can also keep what you already have: bring existing phone numbers over SIP, wire tools to your APIs and MCP servers, or connect your own client over WebSocket.

Most voice stacks stitch together three APIs—speech-to-text, a language model, and text-to-speech—often with each stage hosted by a different provider. Every hop adds cost, latency, and new failure modes. Voice Agent Builder is one interface on a speech-to-speech path built for Grok Voice, tightly coupled to the model rather than assembled from three.

Your browser does not support the video tag.<br>Trained on the hardest calls we could find

Real calls come with low-quality telephony audio, background noise, strong accents, interruptions, and callers who change their minds mid-sentence. The workflows behind them are ambiguous, run across dozens of tools, and happen in any of 25+ languages.

We trained Grok Voice on those calls. τ-voice Bench measures agents under the same conditions.

τ-voice Bench Leaderboard<br>Grok Voice Think Fast 1.0

:host{display:inline-block;direction:ltr;white-space:nowrap;line-height:var(--number-flow-char-height, 1em) !important}span{display:inline-block}:host([data-will-change]) span{will-change:transform}.number,.digit{padding:calc(var(--number-flow-mask-height, 0.25em) / 2) 0}.symbol{white-space:pre}67.367.3%

Gemini 3.1 Flash Live

:host{display:inline-block;direction:ltr;white-space:nowrap;line-height:var(--number-flow-char-height, 1em) !important}span{display:inline-block}:host([data-will-change]) span{will-change:transform}.number,.digit{padding:calc(var(--number-flow-mask-height, 0.25em) / 2) 0}.symbol{white-space:pre}43.843.8%

GPT Realtime 1.5

:host{display:inline-block;direction:ltr;white-space:nowrap;line-height:var(--number-flow-char-height, 1em) !important}span{display:inline-block}:host([data-will-change]) span{will-change:transform}.number,.digit{padding:calc(var(--number-flow-mask-height, 0.25em) / 2) 0}.symbol{white-space:pre}35.335.3%

OverallRetailAirlineTelecom

Two minutes to an agent

Setup is simple: write a plain-language description of how calls should flow, then attach your documents, tools, and guardrails. You can go from zero to a working agent in about two minutes.

Teach it your business

An agent starts with a prompt that describes how calls should go. The model reasons in real time, so it can follow long instructions and work through ambiguous requests.

What it knows comes from the knowledge base . You upload documents in common formats (plain text, Markdown, Word, PowerPoint, Excel, HTML, JSON, and others), and the agent retrieves from them during calls. Documents are organized into collections , which you can attach to one or more agents and share across agents so policies, product specs, and runbooks stay in one place instead of being pasted into every prompt.

Take action

Knowing the business is only half of a support or sales call. Agents also need to act . They look things up, change records, hand off, or close the loop after the conversation.

Tools and connectors are how that happens. On a booking line, the agent might schedule appointments in Google Calendar or Outlook Calendar, then send a confirmation through your email provider. On support, an API request can check order status or issue a refund in your own systems. When the answer isn't only in your documents, web search or X search can pull current public information. Tickets can be managed in Linear or Notion, and files come from Google Drive or OneDrive.

If the caller needs a human, the agent can transfer the...