xAI · 2026-07-01 · major
xAI Voice Agent Builder — no-code builder for production voice agents
xAI's Voice Agent Builder is a no-code platform for production voice agents on Grok Voice. It costs $0.05/min for agent audio plus $0.01/min for telephony on provisioned numbers, with sub-second latency and 25+ languages.

xAI's Voice Agent Builder is a no-code way to ship production voice agents on Grok Voice, priced by the minute.
Quick facts
| Maker | xAI |
|---|---|
| Availability | Public beta |
| Model | grok-voice-latest |
| Agent audio | $0.05 / min |
| Telephony | $0.01 / min (provisioned numbers) |
| Languages | 25+ |
| Integrations | SIP, MCP tools, knowledge base, guardrails |
Pricing
| Agent audio | $0.05 / min |
|---|---|
| Telephony · On provisioned phone numbers | $0.01 / min |
| Provisioned number · Free | $0 |
What is it?
Voice Agent Builder is xAI's no-code console for wiring up production voice agents on top of the Grok Voice model. Developers pick a voice, add tools and a knowledge base, hook up telephony, and have a running agent in about two minutes — no glue code between STT, LLM, and TTS.
How does it work?
The builder wraps xAI's grok-voice-latest speech-to-speech model in a WebSocket runtime with sub-second turn-taking. SIP support lets an agent answer an existing phone number, MCP servers and custom HTTP tools give it hands, and a knowledge-base layer grounds answers on the team's own docs. Guardrails and observability are wired in by default.
Why does it matter?
The flat $0.05/min agent-audio rate — plus $0.01/min for telephony on xAI-provisioned numbers — undercuts the typical vendor stack that bills STT, an LLM, and TTS separately. That opens real voice-agent deployment (support, sales, scheduling, outbound calls) to teams that could not budget the legacy speech stacks.
Who is it for?
Product teams shipping voice agents for support, sales, or telephony workflows
Frequently asked questions
- How much does xAI's Voice Agent Builder cost?
- xAI's Voice Agent Builder charges $0.05 per minute for agent audio and an extra $0.01 per minute when calls run over a provisioned phone number. Provisioning the number itself is free. There is no separate free tier at launch, and the pricing is uniform whether the agent is talking to a person or to a tool.
- Can Voice Agent Builder use my existing phone number?
- Yes — Voice Agent Builder supports SIP, so teams can bring an existing phone number from a carrier or PBX and point it at their xAI agent. That $0.01/min telephony surcharge only kicks in once the call is routed through a provisioned xAI number, so BYO-number setups stay at the flat $0.05/min agent-audio rate.
- What integrations does Voice Agent Builder support?
- Voice Agent Builder ships with SIP telephony, MCP servers, custom HTTP tools, a knowledge-base layer for retrieval, guardrails, and observability out of the box. xAI also lists demo apps for LiveKit, Pipecat, Twilio, Voximplant, WebRTC, and iOS, so most existing voice stacks can drop the agent in without rewriting the transport.
- Is xAI's Voice Agent Builder generally available?
- Voice Agent Builder launched in public beta on 2026-07-01, not full GA. Any developer with an xAI account can build an agent immediately through the no-code console, but xAI is still iterating on features and pricing may change before the product graduates. The underlying grok-voice-latest speech-to-speech model is what powers every agent.
Try it
https://docs.x.ai/docs/guides/voice