xAI Launches No-Code Voice Agent Builder for Grok

SAN FRANCISCO — xAI is making it dramatically easier to put Grok on the phone. On July 1, the company launched Voice Agent Builder, a no-code platform that lets operators and developers stand up a production-ready voice agent in about two minutes — without writing a single line of code.

The tool runs on Grok Voice and bundles telephony, knowledge retrieval, tools, guardrails and observability into one interface, priced at a flat $0.05 per minute of audio with voices included and no separate platform fee. It is the latest in a rapid cadence of Grok releases that has also brought the assistant to Interactive Brokers for AI-powered market research.

One model, not three stitched together

Most voice stacks chain together three separate services — speech-to-text, a language model and text-to-speech — often from different providers, with each hop adding cost, latency and new points of failure. Voice Agent Builder instead runs on a single speech-to-speech path built for Grok Voice and tightly coupled to the model.

xAI says it trained Grok Voice on the hardest calls it could find: noisy telephony audio, strong accents, interruptions and callers who change their minds mid-sentence, across more than 25 languages. On the company's τ-voice benchmark, Grok Voice Think Fast 1.0 scored 67.3%, well ahead of rival real-time voice models.

Two minutes to a working agent

Setup is deliberately simple. Users write a plain-language description of how calls should flow, then attach documents, tools and guardrails. Knowledge lives in uploadable collections — plain text, Markdown, Word, PowerPoint, Excel and more — that the agent retrieves from during calls.

The agents can also act, not just answer. Through tools and connectors, a Grok voice agent can book appointments in Google or Outlook Calendar, check order status, issue refunds, manage tickets in Linear or Notion, pull files from Google Drive or OneDrive, and hand off to a human when needed. Each account includes a free phone number, and existing numbers can be brought over via SIP.

Building an enterprise voice stack

Every call is recorded and transcribed, with playback, tool traces and guardrails that keep agents on-script. The launch extends xAI's enterprise push, which recently made Grok models available on Databricks' Agent Bricks platform for governed enterprise deployments.

The transparent, per-minute pricing is a pointed contrast to competitors that meter recognition, reasoning and synthesis separately. As xAI put it in its announcement, a voice agent is easier to judge by ear than by benchmark — so build one, give it your hardest workflow, and call it.

For xAI, now part of SpaceX, Voice Agent Builder turns Grok Voice from a developer API into a product anyone can deploy — another step toward putting frontier AI into the hands of businesses and creators everywhere.