Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

MODEL · ENTITY #2561

Grok Voice

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · arXiv cs.AI

VAmoS Energy benchmark: tougher, more realistic voice-agent simulation for billing calls

The VAmoS Part Deux paper (arXiv:2609.38512v1) introduces VAmoS Energy, a benchmark of 100 simulated utility-billing calls where each caller makes 2–4 requests and agents use 16 tools (including a Stripe billing twin and Apache Fineract). An LLM-based verifier (99.1% agreement with a code verifier) checks agent actions and spoken figures; across 14 voice stacks, completion rates ranged 17.3%–44.7% (Grok Voice highest), and background television cut pooled completion from 38.7% to 8.6%.

7.0

COMPANIES · 1 SOURCE · xAI

Grok Voice releases Voice Agent Builder (beta) — no-code platform for production voice agents

Grok Voice announced Voice Agent Builder in beta, a no-code platform to configure production voice agents in about two minutes. The integrated speech-to-speech interface bundles telephony, knowledge retrieval, tools/connectors, guardrails, MCPs, observability, optional brand voice cloning and SIP number support; calls are recorded/transcribed and billing is quoted at $0.08/min of audio with telephony on a provisioned number at $0.01/min.

7.0

MODELS · 1 SOURCE · xAI

xAI adds 21 multilingual flagship voices to Grok Voice and upgrades original five

xAI released 21 new flagship voices for Grok Voice, all natively multilingual and available now in the Realtime Voice Agent API, the Text to Speech API, and the Grok Voice Agent Builder. The original five voices (Ara, Eve, Leo, Rex, Sal) were retrained with an improved recipe for more natural pacing, phrasing, and emphasis; developers can also clone a custom voice from about one minute of audio.

6.0