
xAI Announces Grok Voice 3.0 Speech-to-Speech Model
xAI has announced Grok Voice 3.0, a speech-to-speech model that ranks first on Artificial Analysis' Speech-to-Speech Index with a score of 86.9, features sub-one-second latency, and is available in the API at $0.08 per minute.
xAI has announced Grok Voice 3.0, a speech-to-speech model the company calls the world's most intelligent voice model. The release sets a new record for resolving customer support calls, offers latency under one second, and costs less than competing frontier models, according to the announcement.
Benchmark Results
In independent testing by Artificial Analysis, Grok Voice 3.0 ranks first on the Speech-to-Speech Index with a score of 86.9, ahead of GPT-Live-1 (Astra, Medium) at 83.2, Gemini 3.8 Live (Ext. Thinking, High) at 82.6, and its predecessor Grok Voice 2.0 at 81.3. The index combines speech reasoning, tau-Voice, and preference and task success from blind head-to-head calls.
Grok Voice 3.0 scores 98.5% on Big Bench Audio for speech reasoning, 1070 on the Speech Agent Arena Elo for human preference, a 94.8% task success rate, and 97.0% on Full Duplex Bench, which measures how naturally a model handles pauses, turn-taking, and interruptions. On tau-Voice, which tests support calls with diverse accents, background noise, and interruptions, it scores 71.6%, comparable with GPT-Live-1 (Astra) at 74.5%, but with 40% lower latency.
Cost and Enterprise Performance
Artificial Analysis measures the cost to complete a task in its Big Bench Audio run, and Grok Voice 3.0 comes in at $0.025 per task, below GPT-Live-1 (Astra, Medium) at $0.030 and GPT-Realtime-2.1 (High) at $0.055.
On EVA-Bench, ServiceNow's open-source benchmark for enterprise voice agents spanning more than 200 realistic scenarios, Grok Voice 3.0 achieves the highest accuracy score at 74% and is the best-performing model when accuracy and customer experience are scored jointly. Nitin Aggarwal, Senior Director of Product Management, Agentic Evals and RAI at ServiceNow, said the model sets a new Pareto frontier on EVA-Bench and pairs top accuracy with natural, responsive conversation.
Deployment at Tesla and SpaceX
Grok Voice handles millions of conversations a day across Tesla and SpaceX. In Tesla vehicles, drivers use Connectors for simple requests like checking a calendar or answering an email, and Grok Bot for larger tasks like ordering coffee or booking dinner, all hands-free. Grok Voice 3.0 also powers Grok Bot's voice mode.
Starlink call centers use Grok Voice to answer 20,000 customer calls every day in multiple languages. Roughly 70% are resolved with no human in the loop, and one in four sales calls ends in a purchase before the caller hangs up. A single agent built on Grok Voice 3.0 verifies customers, troubleshoots hardware, issues credits, and ships replacement equipment.
Pricing and Availability
Grok Voice 3.0 is available today in the Voice Agent API at $0.08 per minute ($4.80 per hour), the same price as Grok Voice 2.0. Agents using grok-voice-latest have been switched over automatically with no changes needed.
Sources: Spacexsi
SiTech — AI-powered web development
We build fast, modern websites and bring AI into real business workflows. Have a project or a question? We'd love to help.