The Circuitry
THE CIRCUITRYYour one-stop source for all tech news
HOMETODAYNEWSFEEDEVENTS
BOOKMARKS
RSS
© 2026 The Circuitry
About UsSourcesContactCorrectionsPrivacy
  • Today
  • Feed
  • Events
  • Saved
Scroll for more
Verification
VERIFIEDConfidence: HIGH
Source identified
Claims cross-referenced
No discrepancies found
Fact-check summary

Reported directly by xAI — the official primary source for this announcement.

Sourcing
1source

via xAI

Home/Tech/xAI Launches No-Code Voice Agent Builder with Grok Voice
VERIFIEDBy Xavier Rivera· ·2 min read

xAI Launches No-Code Voice Agent Builder with Grok Voice

xAI has launched Voice Agent Builder, a beta no-code platform for creating human-like voice agents with Grok Voice that is available today at $0.05 per minute. The service provides sub-second latency, leads voice benchmarks, integrates with common business tools, and supports enterprise compliance standards.

Source:xAI
Post
xAI Launches No-Code Voice Agent Builder with Grok Voice
TL;DRAI · 60 sec read

xAI launches Voice Agent Builder, a beta no-code platform that creates and deploys Grok Voice agents in under two minutes. It delivers sub-second latency in 25 languages, tops the Tau leaderboard at 67.3 percent, handles messy real calls, and integrates with tools like Gmail while meeting SOC 2 and HIPAA standards.

xAI has released Voice Agent Builder, a beta no-code platform that lets users create and deploy human-like voice agents powered by Grok Voice in under two minutes.

Voice Agent Builder offers sub-second latency and broad language support. The platform delivers warm, expressive voices capable of real conversation timing, tone, and warmth rather than scripted phone-tree responses. It achieves sub-second latency, supports 25+ languages, and is priced at $0.05 per minute. A free phone number is provided or users can bring their own.
Grok Voice agents are trained to manage messy real-world calls.
The service leads the Tau Voice Leaderboard with a Grok Voice Think Fast 1.0 score of 67.3 percent. That compares with Gemini 3.1 Flash Live at 43.8 percent and GPT Realtime 1.5 at 35.3 percent across overall, retail, airline, and telecom categories.
POST FROM @xai· official announcement tweet from xAI launching the Voice Agent Builder
https://x.com/xai/status/2072342803787702422
Grok Voice agents are trained to manage messy real-world calls. The agents handle interruptions, half-remembered order numbers, and additional requests while seeing every call through from greeting to resolution. They pull up records, check policy, and take action mid-conversation for use cases including support, sales, lead qualification, reception, and scheduling.
From The CircuitryThe Feed — live briefs across tech, all day.See what’s happening →
Agents maintain intelligence without sacrificing speed by delivering real reasoning and answers in under a second. They are trained on the hardest calls available and can clear through background noise and strong accents.
Agents maintain intelligence without sacrificing speed by delivering real reasoning and answers in under a second.
Integration with existing tools and enterprise compliance features are built in. Grok plugs directly into Gmail, Google Calendar, Outlook, Linear, Notion, OneDrive, and more to trigger workflows, schedule follow-ups, and send confirmations. Custom MCPs can be integrated for any internal system, database, CRM, or custom workflow. The platform supports direct SIP for major telephony providers, offers user-defined guardrails, and is SOC 2, HIPAA eligible, and GDPR compliant.

Users define agent behavior through simple instructions and knowledge bases. A playbook format lets users describe multi-step workflows such as greeting callers, looking up orders, resolving issues, and wrapping up with confirmation. Knowledge bases accept plain text, Markdown, and PDFs that the agent references during calls. Changes to instructions or documents update agent behavior instantly.
The builder includes a live preview where users can talk to the agent in the browser and hear updates in real time. Playback of any call is available from start to finish. Custom voices can be selected from a library of more than 80 built-in options across 25+ languages or cloned from two minutes of audio.
Why this mattersAI · ~100 words

Tap a lens to see what this story means for you.

Reader-supported
DonateBuy me a coffee →Follow@thecircuitry_ →Follow@thecircuitry.to →

Reader-supported · The Brief

Liked this? The Brief brings you the whole day in tech, verified, every morning. Two minutes, free forever.

HELP US IMPROVE
From The Circuitry

See what’s happening right now

The Feed runs all day — short, verified briefs the moment they break.

Open the Feed →
From The Circuitry

Follow @thecircuitry_

Every story we publish, as it happens. No noise between.

Follow on X ↗On Bluesky ↗

Reader-supported

The Circuitry is a passion project I've always wanted to build, and I love the work behind it.

Running it costs real money. APIs, hosting, time. To keep improving the site and growing this into something useful for everyone, those costs have to be covered.

Any contribution is appreciated. If not, no pressure. Thanks for reading.

Buy me a coffee
xAIGrokVoice AINo-Code
More inTech
  • Tesla and SpaceX confirm Terafab chip fab in Texas

    Tech · 1d
  • OpenAI Urges Federal Judge to Throw Out Apple's Trade Secrets Complaint

    Tech · 2d
  • Meta introduces Muse Code, its terminal-based coding agent

    Tech · 2d
SupportThe Work

The Circuitry is reader-supported. If you find the daily brief useful, you can buy me a coffee to keep it going.

Buy a coffee →
SubscribeCircuitry Brief

Liked this? The Brief brings you the whole day in tech, verified, every morning. Free forever.

MORE IN TECH

Tesla and SpaceX confirm Terafab chip fab in Texas

Tesla and SpaceX have confirmed Grimes County, Texas as the site for their Terafab semiconductor megafactory, with the first phase costing roughly $16.8 billion. The project targets the largest chip manufacturing facility on the planet to supply over 1 terawatt of compute per year that exceeds current and future global production capacity.

OpenAI Urges Federal Judge to Throw Out Apple's Trade Secrets Complaint

OpenAI has filed a motion asking a federal judge to dismiss Apple's trade secrets lawsuit, describing the claims as meritless. The dispute, which follows a July suit and this week's injunction request from Apple, highlights tensions after their prior partnership on Siri and OpenAI's hardware push.

Meta introduces Muse Code, its terminal-based coding agent

Meta has released an early beta of Muse Code, a terminal-based coding agent driven by the updated Muse Spark 1.2 model and positioned against Anthropic's Claude Code and OpenAI's Codex. Substantially lower rates, including a contributor plan at $0.10 for every million tokens received, may encourage migration away from higher-priced options such as Anthropic's Sonnet 5.