Meet Grok Voice 3.0: SpaceXAI Voice Agent Model Ranks #1 on Artificial Analysis

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.

Back&lt;/button&gt;&lt;button class=&quot;btn&quot; id=&quot;gvNext&quot;&gt;Next <img src="https://s.w.org/images/core/emoji/17.0.2/72x72/25b6.png" alt="▶" class="wp-smiley" style="height: 1em; max-height: 1em;" />&lt;/button&gt;&lt;button class=&quot;btn&quot; id=&quot;gvPlay&quot;&gt;Auto-play&lt;/button&gt;&lt;/div&gt; &lt;/div&gt; &lt;div class=&quot;pnl&quot; id=&quot;p2&quot;&gt; &lt;div class=&quot;chips&quot; id=&quot;gvChips&quot;&gt;&lt;/div&gt; &lt;div id=&quot;gvBars&quot;&gt;&lt;/div&gt; &lt;p class=&quot;note&quot; id=&quot;gvNote&quot;&gt;&lt;/p&gt; &lt;/div&gt; &lt;div class=&quot;pnl&quot; id=&quot;p3&quot;&gt; &lt;svg viewBox=&quot;0 0 640 330&quot; width=&quot;100%&quot; role=&quot;img&quot; aria-label=&quot;τ-Voice success rate versus time to first audio&quot;&gt; &lt;rect x=&quot;0&quot; y=&quot;0&quot; width=&quot;640&quot; height=&quot;330&quot; fill=&quot;transparent&quot;/&gt; &lt;g stroke=&quot;#2a2a2a&quot;&gt; &lt;line x1=&quot;70&quot; y1=&quot;30&quot; x2=&quot;70&quot; y2=&quot;280&quot;/&gt;&lt;line x1=&quot;70&quot; y1=&quot;280&quot; x2=&quot;610&quot; y2=&quot;280&quot;/&gt; &lt;line x1=&quot;70&quot; y1=&quot;196.7&quot; x2=&quot;610&quot; y2=&quot;196.7&quot; stroke-dasharray=&quot;3 4&quot;/&gt;&lt;line x1=&quot;70&quot; y1=&quot;113.3&quot; x2=&quot;610&quot; y2=&quot;113.3&quot; stroke-dasharray=&quot;3 4&quot;/&gt; &lt;line x1=&quot;70&quot; y1=&quot;30&quot; x2=&quot;610&quot; y2=&quot;30&quot; stroke-dasharray=&quot;3 4&quot;/&gt; &lt;/g&gt; &lt;g fill=&quot;#9a9a9a&quot; font-size=&quot;11&quot;&gt; &lt;text x=&quot;62&quot; y=&quot;284&quot; text-anchor=&quot;end&quot;&gt;50%&lt;/text&gt;&lt;text x=&quot;62&quot; y=&quot;201&quot; text-anchor=&quot;end&quot;&gt;60%&lt;/text&gt;&lt;text x=&quot;62&quot; y=&quot;117&quot; text-anchor=&quot;end&quot;&gt;70%&lt;/text&gt;&lt;text x=&quot;62&quot; y=&quot;34&quot; text-anchor=&quot;end&quot;&gt;80%&lt;/text&gt; &lt;text x=&quot;70&quot; y=&quot;298&quot; text-anchor=&quot;middle&quot;&gt;0.5 s&lt;/text&gt;&lt;text x=&quot;205&quot; y=&quot;298&quot; text-anchor=&quot;middle&quot;&gt;0.75 s&lt;/text&gt;&lt;text x=&quot;340&quot; y=&quot;298&quot; text-anchor=&quot;middle&quot;&gt;1.0 s&lt;/text&gt;&lt;text x=&quot;475&quot; y=&quot;298&quot; text-anchor=&quot;middle&quot;&gt;1.25 s&lt;/text&gt;&lt;text x=&quot;610&quot; y=&quot;298&quot; text-anchor=&quot;middle&quot;&gt;1.5 s&lt;/text&gt; &lt;text x=&quot;340&quot; y=&quot;320&quot; text-anchor=&quot;middle&quot;&gt;Time to first audio (lower is faster)&lt;/text&gt; &lt;text x=&quot;16&quot; y=&quot;155&quot; text-anchor=&quot;middle&quot; transform=&quot;rotate(-90 16 155)&quot;&gt;τ-Voice success&lt;/text&gt; &lt;/g&gt; &lt;text x=&quot;84&quot; y=&quot;50&quot; fill=&quot;#ffffff&quot; font-size=&quot;12&quot; font-weight=&quot;700&quot;&gt;<img src="https://s.w.org/images/core/emoji/17.0.2/72x72/2196.png" alt="↖" class="wp-smiley" style="height: 1em; max-height: 1em;" /> better&lt;/text&gt; &lt;g id=&quot;gvDots&quot;&gt;&lt;/g&gt; &lt;/svg&gt; &lt;p class=&quot;note&quot;&gt;Source: Artificial Analysis, accessed October 14, 2026. Grok Voice 3.0 trails GPT-Live-1 (Astra, medium) by 2.9 points on τ-Voice but reaches first audio 0.53 s sooner.&lt;/p&gt; &lt;/div&gt; &lt;div class=&quot;pnl&quot; id=&quot;p4&quot;&gt; &lt;div class=&quot;kv&quot;&gt; &lt;div class=&quot;k&quot;&gt;&lt;b&gt;$0.08/min&lt;/b&gt;&lt;span&gt;$4.80/hr, same as Grok Voice 2.0&lt;/span&gt;&lt;/div&gt; &lt;div class=&quot;k&quot;&gt;&lt;b&gt;0.81 s&lt;/b&gt;&lt;span&gt;time to first audio (AA)&lt;/span&gt;&lt;/div&gt; &lt;div class=&quot;k&quot;&gt;&lt;b&gt;28&lt;/b&gt;&lt;span&gt;built-in voices, plus cloning&lt;/span&gt;&lt;/div&gt; &lt;div class=&quot;k&quot;&gt;&lt;b&gt;20&lt;/b&gt;&lt;span&gt;listed locales, auto-detected&lt;/span&gt;&lt;/div&gt; &lt;div class=&quot;k&quot;&gt;&lt;b&gt;5&lt;/b&gt;&lt;span&gt;tool types: files, web, X, MCP, functions&lt;/span&gt;&lt;/div&gt; &lt;div class=&quot;k&quot;&gt;&lt;b&gt;SIP&lt;/b&gt;&lt;span&gt;phone and contact-center routing&lt;/span&gt;&lt;/div&gt; &lt;/div&gt; &lt;pre&gt;&lt;code&gt;wss://api.x.ai/v1/realtime?model=grok-voice-3.0 {&quot;type&quot;: &quot;session.update&quot;, &quot;session&quot;: { &quot;voice&quot;: &quot;eve&quot;, &quot;reasoning&quot;: {&quot;effort&quot;: &quot;high&quot;}, &quot;turn_detection&quot;: {&quot;type&quot;: &quot;server_vad&quot;}, &quot;tools&quot;: [{&quot;type&quot;: &quot;web_search&quot;}] }}&lt;/code&gt;&lt;/pre&gt; &lt;p class=&quot;note&quot;&gt;The &lt;code&gt;grok-voice-latest&lt;/code&gt; alias already points to &lt;code&gt;grok-voice-3.0&lt;/code&gt;. Pin the versioned name in production. Grok Voice 2.0 is deprecated.&lt;/p&gt; &lt;/div&gt; &lt;div class=&quot;ft&quot;&gt;&lt;span&gt;Data: &lt;a href=&quot;https://x.ai/news/grok-voice-3&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot;&gt;SpaceXAI&lt;/a&gt;, &lt;a href=&quot;https://artificialanalysis.ai/speech-to-speech&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot;&gt;Artificial Analysis&lt;/a&gt;, &lt;a href=&quot;https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot;&gt;SpaceXAI docs&lt;/a&gt;&lt;/span&gt;&lt;span class=&quot;brand&quot;&gt;© Marktechpost&lt;/span&gt;&lt;/div&gt; &lt;/div&gt; &lt;script&gt; (function(){ var R=document.getElementById('mtp-gv3'); function post(){try{parent.postMessage({mtpEmbed:'gv3',height:R.offsetHeight+40},'*')}catch(e){}} R.querySelectorAll('.tab').forEach(function(t){t.addEventListener('click',function(){ R.querySelectorAll('.tab').forEach(function(x){x.classList.remove('on')}); R.querySelectorAll('.pnl').forEach(function(x){x.classList.remove('on')}); t.classList.add('on');document.getElementById(t.dataset.p).classList.add('on'); if(t.dataset.p==='p2')drawBars();if(t.dataset.p==='p3')drawDots();setTimeout(post,60);});}); /* wave */ var w=document.getElementById('gvWave');for(var i=0;i&lt;48;i++){var b=document.createElement('i');b.style.animationDelay=(i*0.045)+'s';w.appendChild(b);} /* pipeline */ var S=[ ['Caller speaks','Audio streams over a WebSocket (or SIP for phone calls) as PCM at 8 to 48 kHz, G.711 or Opus.'], ['Turn detection','Server-side voice activity detection decides when the caller has finished, and handles barge-in when they interrupt.'], ['Reasoning','Reasoning is on by default with reasoning.effort set to &quot;high&quot;. Set it to &quot;none&quot; for faster, simpler turns.'], ['Tools','The agent can call collections search, web search, X search, remote MCP servers and your own functions mid-call.'], ['Reply streams','Audio deltas stream back as soon as they are ready. Artificial Analysis measures 0.81 s to first audio.']]; var F=document.getElementById('gvFlow'),cur=0,timer=null; S.forEach(function(s,i){var b=document.createElement('button');b.className='st';b.innerHTML='&lt;div class=&quot;n&quot;&gt;STEP '+(i+1)+'&lt;/div&gt;&lt;div class=&quot;t&quot;&gt;'+s[0]+'&lt;/div&gt;'; b.addEventListener('click',function(){stop();show(i)});F.appendChild(b);}); function show(i){cur=(i+S.length)%S.length;F.querySelectorAll('.st').forEach(function(x,j){x.classList.toggle('on',j===cur)}); document.getElementById('gvDt').textContent=S[cur][0];document.getElementById('gvDp').textContent=S[cur][1];} function stop(){if(timer){clearInterval(timer);timer=null;document.getElementById('gvPlay').textContent='Auto-play';}} document.getElementById('gvPrev').onclick=function(){stop();show(cur-1)}; document.getElementById('gvNext').onclick=function(){stop();show(cur+1)}; document.getElementById('gvPlay').onclick=function(){if(timer){stop();return}this.textContent='Pause';timer=setInterval(function(){show(cur+1)},2200)}; show(0); /* bars */ var M=['Grok Voice 3.0','Grok Voice 2.0','GPT-Live-1 (Astra, medium)','Gemini 3.8 Live Ext. Thinking']; var B={ 'AA Index':{v:[86.9,81.3,83.2,82.6],max:100,f:function(x){return x.toFixed(1)},n:'Equal-weighted average of Big Bench Audio, τ-Voice, Arena preference and task success.'}, 'Big Bench Audio':{v:[98.5,97.2,90.1,97.7],max:100,f:function(x){return x.toFixed(1)+'%'},n:'Speech reasoning. Grok Voice 3.0 ranks 4th overall; StepAudio 3 Realtime leads at 99.7%.'}, 'τ-Voice':{v:[71.6,56.5,74.5,68.6],max:100,f:function(x){return x.toFixed(1)+'%'},n:'Replica customer-support calls with tools. GPT-Live-1 (Astra, medium) leads this group.'}, 'Full Duplex Bench':{v:[97.0,95.1,94.9,91.9],max:100,f:function(x){return x.toFixed(1)+'%'},n:'Pauses, turn-taking, interruptions and backchannels.'}, 'Task success':{v:[94.8,94.6,87.4,89.1],max:100,f:function(x){return x.toFixed(1)+'%'},n:'Share of conversations ending in the correct final tool call.'}, 'Arena Elo':{v:[1070,1011,1056,993],max:1100,f:function(x){return String(x)},n:'Live Speech Agent Arena Elo on Artificial Analysis. Higher is preferred.'}, 'Time to first audio':{v:[0.81,0.70,1.34,1.35],max:1.5,f:function(x){return x.toFixed(2)+' s'},n:'Lower is faster. Grok Voice 2.0 was quicker than 3.0.'}}; var C=document.getElementById('gvChips'),BR=document.getElementById('gvBars'),key='AA Index'; Object.keys(B).forEach(function(k){var c=document.createElement('button');c.className='chip'+(k===key?' on':'');c.textContent=k; c.onclick=function(){key=k;C.querySelectorAll('.chip').forEach(function(x){x.classList.toggle('on',x===c)});drawBars()};C.appendChild(c);}); M.forEach(function(m,i){var r=document.createElement('div');r.className='row'; r.innerHTML='&lt;div class=&quot;lbl&quot;&gt;'+m+'&lt;/div&gt;&lt;div class=&quot;trk&quot;&gt;&lt;div class=&quot;fill'+(i===0?' me':'')+'&quot;&gt;&lt;/div&gt;&lt;/div&gt;&lt;div class=&quot;val&quot;&gt;&lt;/div&gt;';BR.appendChild(r);}); function drawBars(){var d=B[key];BR.querySelectorAll('.row').forEach(function(r,i){var f=r.querySelector('.fill');f.style.width='0'; r.querySelector('.val').textContent=d.f(d.v[i]);setTimeout(function(){f.style.width=(d.v[i]/d.max*100)+'%'},40+i*90)}); document.getElementById('gvNote').textContent=d.n+' Source: Artificial Analysis / SpaceXAI.';} drawBars(); /* scatter */ var P=[['Grok Voice 3.0','0.81 s · 71.6%',0.81,71.6,1,'r'],['Grok Voice 2.0','0.70 s · 56.5%',0.70,56.5,0,'r'],['GPT-Live-1 (Astra, medium)','1.34 s · 74.5%',1.34,74.5,0,'l'],['Gemini 3.8 Live Ext. Thinking','1.35 s · 68.6%',1.35,68.6,0,'l']]; var G=document.getElementById('gvDots'),NS='http://www.w3.org/2000/svg'; P.forEach(function(p){var x=70+(p[2]-0.5)*540,y=280-(p[3]-50)/30*250;var g=document.createElementNS(NS,'g');g.setAttribute('class','dot'); var c=document.createElementNS(NS,'circle');c.setAttribute('cx',x);c.setAttribute('cy',y);c.setAttribute('r',p[4]?9:7); c.setAttribute('fill',p[4]?'#ffffff':'#5c5c5c');c.setAttribute('stroke',p[4]?'#ffffff':'#9a9a9a');g.appendChild(c); [[p[0],0,p[4]?'700':'600'],[p[1],15,'500']].forEach(function(L){var t=document.createElementNS(NS,'text'); t.setAttribute('x',p[5]==='r'?x+14:x-14);t.setAttribute('y',y-2+L[1]);t.setAttribute('text-anchor',p[5]==='r'?'start':'end'); t.setAttribute('fill',p[4]?'#ffffff':'#bdbdbd');t.setAttribute('font-size','12');t.setAttribute('font-weight',L[2]);t.textContent=L[0];g.appendChild(t);}); G.appendChild(g);}); function drawDots(){G.querySelectorAll('.dot').forEach(function(g,i){g.style.opacity='0';g.style.transform='translateY(30px)'; setTimeout(function(){g.style.opacity='1';g.style.transform='none'},80+i*150)});} window.addEventListener('load',post);window.addEventListener('resize',post);setTimeout(post,300); })(); &lt;/script&gt; &lt;/body&gt; &lt;/html&gt; ">

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

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.