Markdown edition

# Grok Voice 3.0 gains on support test, slows first audio

> The hosted Voice Agent API now uses Grok Voice 3.0. An independent simulated support score rises, while first-audio time increases and the listed voice price has a separate text charge.

By BIG CHANGE Editorial

Published: 2026-10-15T16:54:16.962Z
Updated: 2026-10-15T16:54:16.962Z
Canonical: https://bigchange.ai/blog/grok-voice-3-api-benchmark-support-calls

![Conceptual charcoal illustration of an unbranded call headset and tabletop speakerphone in a sound-treated room.](https://bigchange.ai/api/media/file/grok-voice-support-call-concept-v1.png)
AI-generated conceptual illustration by BIG CHANGE; no actual xAI hardware, API interface, customer call or measured outcome is depicted.

xAI released Grok Voice 3.0 through its hosted Voice Agent API on October 14. For a team choosing a voice agent for customer support, [Artificial Analysis's current speech-to-speech table](https://artificialanalysis.ai/speech-to-speech) shows a 15.1 percentage-point gain on simulated support tasks over Grok Voice 2.0, a small change in its separate task-success measure, and a slower first audio response.

xAI says the `grok-voice-latest` alias now routes to 3.0 automatically. The [current API guide](https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech) also offers a versioned `grok-voice-3.0` name for teams that need to pin the release. The WebSocket endpoint, session parameters and events remain the same as in 2.0, according to xAI. No application migration is needed for users of the alias, although a new model behind a moving alias is a reason to rerun an application's own call tests.

## The big change

- **What changed:** Grok Voice 3.0 replaced 2.0 behind the `grok-voice-latest` API alias. Artificial Analysis now reports a 71.6% score on its simulated customer-support benchmark, up from 56.5% for 2.0.
- **Why it matters:** That measure tests whether an agent reaches the correct database state across scripted airline, retail and telecom problems. It is more relevant to a support workflow than a general audio reasoning score, although it is still a simulation.
- **What to watch:** The same evaluator measured 0.81 seconds to first audio for 3.0, against 0.70 seconds for 2.0. Teams should check their own response time, task completion and billable session length before switching a pinned deployment.

## The support score and the response delay

Artificial Analysis's [methodology](https://artificialanalysis.ai/methodology/speech-to-speech-benchmarking) describes its τ-Voice test as a simulated customer calling an agent equipped with a policy document and domain-specific tools. Its airline, retail and telecom tasks have defined final database states, and the score averages three trials. The current table gives Grok Voice 3.0 71.6%, compared with 56.5% for Grok Voice 2.0: a 15.1 percentage-point rise under those test conditions. The evaluation uses a simulated customer, generated speech, transcription and a model grader. It does not measure the share of real callers whose problems a deployed service resolves.

The separate Speech Agent Arena task-success figure moves only from 94.6% for 2.0 to 94.8% for 3.0. That figure counts eligible conversations with the correct final task-completing tool calls; it uses a different test from τ-Voice. The overall Artificial Analysis index rises from 81.3 to 86.9. Its current version gives equal weight to audio reasoning, τ-Voice, blind caller preference and Arena task success. None of those figures alone establishes a gain on every customer-service task.

For speed, Artificial Analysis reports average time to first audio on its Big Bench Audio questions. Grok Voice 3.0 takes 0.81 seconds and 2.0 takes 0.70 seconds. The new model therefore took 0.11 seconds longer to start speaking in that test, even though xAI calls its latency “under one second” in the [release announcement](https://x.ai/news/grok-voice-3). The measure ends at the first audio output; it is not a full-call latency or resolution-time measure.

## What the listed voice price covers

xAI lists both versions at $0.08 per minute, or $4.80 per hour, for speech-to-speech audio. Its [model pricing page](https://docs.x.ai/developers/models/speech-to-speech) adds $0.004 for each billable `conversation.item.create` text event. With the default `server_vad` turn detection, the audio meter counts session duration. With push-to-talk, it counts audio sent and received. An always-open ten-minute session at the listed duration rate therefore has $0.80 in audio charges before any separately billed text events. That calculation is based on xAI's rate card, not a BIG CHANGE invoice or a tested call.

Developers need an xAI API key for a server-side WebSocket connection, or a short-lived token for a client application. The [API guide](https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech) documents `wss://api.x.ai/v1/realtime`, a `model` query parameter, a `session.update` event for instructions, voice and turn detection, and streamed audio events in reply. xAI lists a ten-session concurrent limit per team and a 120-minute maximum session. A support team would still have to supply its own policies, tools, customer data boundaries and escalation workflow; the published benchmark configuration does not establish how that specific implementation will perform.

xAI also reports that Starlink handles 20,000 calls a day with Grok Voice and resolves about 70% without a human. Those are [company-reported operating figures](https://x.ai/news/grok-voice-3); Artificial Analysis's synthetic tests do not verify them. BIG CHANGE reviewed the release, API and benchmark documentation. We did not use the API, call a support agent or reproduce the evaluation.

## Sources & further reading

- [xAI: Introducing Grok Voice 3.0](https://x.ai/news/grok-voice-3), October 14, 2026. Announces availability, the alias change and company-reported deployments.
- [Artificial Analysis: speech-to-speech leaderboard](https://artificialanalysis.ai/speech-to-speech), checked October 15, 2026. Current 3.0 and 2.0 rows for the index, τ-Voice, Arena task success and time to first audio; the table can change as evaluations are updated.
- [Artificial Analysis: benchmarking methodology](https://artificialanalysis.ai/methodology/speech-to-speech-benchmarking), checked October 15, 2026. Defines the index, simulated support test, Arena task-success measure and speed test.
- [xAI: speech-to-speech API guide](https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech), last updated October 13, 2026. Documents model names, migration, WebSocket interface, authentication and session setup.
- [xAI: speech-to-speech pricing and limits](https://docs.x.ai/developers/models/speech-to-speech), last updated September 22, 2026 and checked October 15. Lists audio and text-input rates, metering modes, concurrency and session limits.

## Sources

- [Introducing Grok Voice 3.0](https://x.ai/news/grok-voice-3) — Original hosted API release, alias switch and company-attributed deployment claims.
- [Speech to Speech AI Model & Provider Leaderboard](https://artificialanalysis.ai/speech-to-speech) — Live 3.0 and 2.0 rows for index, tau-Voice, Arena task success and first-audio time; values can update.
- [Speech to Speech Benchmarking Methodology](https://artificialanalysis.ai/methodology/speech-to-speech-benchmarking) — Index v2.0, simulated support benchmark, Arena task success and TTFA definitions.
- [Speech to Speech API Guide](https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech) — Alias, version pinning, WebSocket interface, authentication, session parameters and migration.
- [Speech to Speech Pricing and Rate Limits](https://docs.x.ai/developers/models/speech-to-speech) — Current 3.0 audio and text-event rates, metering modes and session limits.