Today, we’re announcing Grok Voice 3.0, the world’s most intelligent speech-to-speech model. It sets a new record for resolving customer support calls, has class-leading latency at under one second, and costs less than other frontier models. Grok Voice powers millions of conversations a day across Tesla and SpaceX, and is available today in the API at the same price as its predecessor.
\nIn Artificial Analysis’s independent testing, Grok Voice 3.0 ranks #1 on the Speech-to-Speech Index, with a score of 86.9. The Index combines speech reasoning, τ-Voice, and preference and task success from blind head-to-head calls. Grok Voice 3.0 also scores 97% on Full Duplex Bench, a measure of how naturally it handles pauses, turn-taking, and interruptions.
\nSpeech-to-speech benchmark comparison between Grok Voice 3.0 and competing models, per Artificial Analysis.
\n| Benchmark | \nGrok Voice 3.0 (this release) | \nGrok Voice 2.0 | \nGPT-Live-1 (Astra, Medium) | \nGemini 3.8 Live (Ext. Thinking, High) | \n
|---|---|---|---|---|
| 86.9 | \n81.3 | \n83.2 | \n82.6 | \n\n |
| 98.5% | \n97.2% | \n90.1% | \n97.7% | \n\n |
| 1070 | \n1011 | \n1048 | \n990 | \n\n |
| 94.8% | \n94.6% | \n87.4% | \n89.1% | \n\n |
| 97.0% | \n95.1% | \n94.9% | \n91.9% | \n\n |
τ-Voice measures how well agents handle support calls with diverse accents, background noise, and interruptions. Grok Voice 3.0 scores 71.6%, comparable with GPT-Live-1 (Astra), but at 40% lower latency, setting a new frontier in agent intelligence versus responsiveness.
\nIt's also cheaper to run than comparable models. Artificial Analysis measures what each model costs to complete a task in its Big Bench Audio run, and Grok Voice 3.0 comes in under both GPT-Live-1 (Astra, Medium) and GPT-Realtime-2.1.
\nLower cost per task than comparable models
\nAverage cost per task on Artificial Analysis's Big Bench Audio run, USD. Lower is better.
\nOn EVA-Bench, ServiceNow’s benchmark for enterprise voice agents, Grok Voice 3.0 achieves the highest accuracy score at 74% and is the best-performing model when jointly scored across accuracy and customer experience.
\n\n\n“Grok Voice 3.0 sets a new Pareto frontier on EVA-Bench, ServiceNow’s open-source benchmark scoring voice agents on accuracy and experience across 200+ realistic enterprise scenarios. It pairs top accuracy with a natural, responsive conversation, setting a new standard for what enterprises can expect from AI on the front line of customer service.”
\n
Nitin Aggarwal, Senior Director of Product Management, Agentic Evals and RAI, ServiceNow
\nGrok Voice 3.0 handles millions of conversations a day in Tesla vehicles. Drivers can use Connectors for simple requests like checking their calendar or answering an email, and Grok Bot for bigger tasks like ordering a coffee or booking dinner—all completely hands-free (see it on X). Grok Voice 3.0 also powers Grok Bot’s voice mode.
\nStarlink call centers use Grok Voice to answer 20,000 customer calls every day across 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.
\nGrok Voice 3.0 is available today in the Voice Agent API at $0.08 / min ($4.80 / hr), the same price as Grok Voice 2.0. Agents using grok-voice-latest have already been switched over automatically, with no changes needed.