SpaceXAI 发布 Grok Voice 3.0，登顶 AA 语音对话指数

Add as a preferredsource on Google

SpaceXAI just released Grok Voice 3.0. Grok Voice 3.0 is a SpaceXAI speech-to-speech model that listens, reasons, calls tools and speaks. It now ranks first on the Artificial Analysis Speech-to-Speech Index with a score of 86.9. For developers, the endpoint, events and $0.08 per minute price are unchanged from Grok Voice 2.0.

TL;DR

Runs on: SpaceXAI’s hosted Voice Agent API only. No open weights, no local or quantized variants.

Performance: Highest Index score of any model Artificial Analysis currently ranks.

Best: 86.9 on the AA Speech-to-Speech Index, ranked #1.

Worst: 71.6% on τ-Voice, behind GPT-Live-1 (Astra, medium) at 74.5%.

Bottom line:

Best: top composite score at 0.81 s time to first audio.

Worst: not the leader on agentic task resolution or raw speech reasoning.

What is Grok Voice 3.0?

Grok Voice 3.0 is SpaceXAI’s flagship realtime voice model, exposed as grok-voice-3.0 on the /v1/realtime WebSocket endpoint. The grok-voice-latest alias already points to it, so existing agents switched automatically.

SpaceXAI has not published parameter counts or architecture details. Reasoning is on by default (reasoning.effort: "high") and can be set to "none" for faster turns. Server-side voice activity detection handles barge-in. Tools run inside the session: collections search, web search, X search, remote MCP servers and custom functions.

How does Grok Voice 3.0 perform on benchmarks?

The AA Speech-to-Speech Index is an equal-weighted average of 4 components. Those are Big Bench Audio reasoning, τ-Voice agentic performance, Speech Agent Arena preference and task success rate.

Grok Voice 3.0 scores 86.9. GPT-Live-1 (Astra, medium) scores 83.2, Gemini 3.8 Live Extended Thinking 82.6. Grok Voice 2.0 scored 81.3.

Component results are strong, not uniformly first:

Big Bench Audio: 98.5%, ranked 4th. StepAudio 3 Realtime leads at 99.7%.

Full Duplex Bench: 97.0%, ranked 4th. StepAudio 3 Realtime leads at 98.9%.

Task success rate: 94.8%, up from 94.6% for Grok Voice 2.0.

Speech Agent Arena Elo: 1070, the highest among the 4 models compared here.

τ-Voice: 71.6%, up from 56.5%, but below GPT-Live-1 (Astra, medium) at 74.5%.

ServiceNow’s EVA-Bench scores enterprise voice agents on accuracy and experience. SpaceXAI reports a top accuracy score of 74%.

Is Grok Voice 3.0 fast and cheap?

Artificial Analysis measures 0.81 s time to first audio. GPT-Live-1 (Astra, medium) measures 1.34 s, so SpaceXAI’s “40% lower latency” claim checks out. Grok Voice 2.0 was faster, though, at 0.70 s.

On cost, SpaceXAI cites Artificial Analysis cost per Big Bench Audio task. Grok Voice 3.0 costs $0.025 per task, versus $0.030 for GPT-Live-1 (Astra, medium) and $0.055 for GPT-Realtime-2.1 (High). On AA’s cost per hour of input audio, Gemini 3.8 Live Extended Thinking is cheaper: $3.50 versus $4.80.

List prices are not directly comparable. GPT-Live-1 costs $0.05 per minute, but backend model and tool usage is billed separately. Gemini 3.8 Live bills audio per minute plus text tokens.

How does Grok Voice 3.0 compare to GPT-Live-1 and Gemini 3.8 Live?

FeatureGrok Voice 3.0Grok Voice 2.0GPT-Live-1 (Astra, medium)Gemini 3.8 Live Extended Thinking

DeveloperSpaceXAISpaceXAIOpenAIGoogle

ParametersNot disclosedNot disclosedNot disclosedNot disclosed

Context lengthNot disclosedNot disclosedNot disclosedNot disclosed

WeightsClosed, API onlyClosed, deprecatedClosed, API onlyClosed, API only

Input / outputAudio, text / audio, textAudio, text / audio, textAudio, text / audio, textText, image, video, audio / audio, text

AA Speech-to-Speech Index86.981.383.282.6

Big Bench Audio98.5%97.2%90.1%97.7%

τ-Voice71.6%56.5%74.5%68.6%

Full Duplex Bench97.0%95.1%94.9%91.9%

Task success rate94.8%94.6%87.4%89.1%

Arena Elo (AA live)107010111056993

Time to first audio0.81 s0.70 s1.34 s1.35 s

AA cost per hour input audio$4.80$4.80$5.83$3.50

List price$0.08/min$0.08/min$0.05/min plus backend usage$0.005/min audio in, $0.018/min audio out, plus text tokens

Benchmark data: Artificial Analysis, accessed October 14, 2026. SpaceXAI’s blog lists frozen Arena Elo values of 1048 (GPT-Live-1) and 990 (Gemini).

How do developers deploy Grok Voice 3.0?

The API is compatible with the OpenAI Realtime API, so migration mostly means a new URL and key.

Transports: WebSocket, WebRTC demo apps, and SIP for phone and contact-center calls.

Audio: PCM at 8 to 48 kHz, G.711 μ-law and A-law, and Opus.

Voices: 28 built-in voices, plus custom voices cloned from a reference clip of up to 120 s.

Languages: 20 listed locales with automatic language detection.

Extensions: force_message for scripted lines, pronunciation replace maps, and 30-minute session resumption.

Compliance: SOC 2 Type II, HIPAA eligible with a BAA, and GDPR. SpaceXAI says audio is not stored or used for training.

Production teams should pin grok-voice-3.0 rather than the alias. Grok Voice 2.0 is now deprecated.

Key Takeaways

Grok Voice 3.0 ranks #1 on the AA Speech-to-Speech Index at 86.9.

It answers in 0.81 s, 40% lower latency than GPT-Live-1 (Astra, medium).

τ-Voice jumped to 71.6%, but GPT-Live-1 still leads at 74.5%.

Price stays at $0.08 per minute, and grok-voice-latest upgraded automatically.

It is API only: no weights, no disclosed size.

Michal Sutter+ postsBio ⮌

Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights.

Michal SutterZ.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB

SpaceXAI 发布 Grok Voice 3.0，登顶 AA 语音对话指数

推荐理由

主题

标签

正文