Grok Voice 3.0 ranks first on Artificial Analysis speech index, third in arena
Article timeline
The articles in this story. Times are ET.
Elon Musk@elonmuskXGrok Voice 3.0 is introduced as a speech-to-speech modelAIxAI introduces Grok Voice 3.0, which it calls the world's most intelligent speech-to-speech model. The company says it resolves customer calls well, responds in under a second, and costs less than other frontier models. Elon Musk's post simply asks readers to try Grok Voice.
🚨 AI News | TestingCatalog@testingcatalogXGrok Voice 3.0 claims state-of-the-art speech-to-speech results with 40% lower latencyAISpaceXSI announces Grok Voice 3.0, which it says is state-of-the-art on many benchmarks and the Artificial Analysis Speech-to-Speech Index. The model has 40% lower latency and responds in under a second, according to the company's announcement. SpaceXSI also says it costs less than other frontier models.
Rohan Paul@rohanpaul_aiXGrok Voice 3.0 tops Artificial Analysis's Speech-to-Speech Index at 86.9AIArtificial Analysis ranks Grok Voice 3.0 first on its Speech-to-Speech Index, which it says blends spoken reasoning, simulated support calls, blind preference votes and task success. The post says Grok Voice 3.0 runs inside Tesla vehicles, handling millions of conversations a day for hands-free requests such as calendar checks and coffee orders. It also powers Grok Bot's voice mode.
Artificial Analysis@ArtificialAnlysOfficialGrok Voice 3.0 debuts third in Speech Agent Arena at Elo 1070AIGrok Voice 3.0 debuts at #3 in Artificial Analysis's Speech Agent Arena with an Elo of 1070, behind Gemini 3.1 Flash Live Minimal (1100) and Gemini 3.8 Live (1088). It ranks #1 on Task Success Rate at 94.8%, ahead of Gemini 3.8 Live at 93.2%, while Grok Voice 2.0 scores Elo 1011 with a 94.6% Task Success Rate.
- Artificial Analysis@ArtificialAnlysOfficialPickGrok Voice 3.0 debuts at #1 on Artificial Analysis Speech to Speech Index
AIArtificial Analysis says SpaceXAI's Grok Voice 3.0 debuts at #1 on its Speech to Speech Index with a score of 86.9, ahead of GPT-Live-1 (Astra, medium) at 83.2. The model ranks #1 on Task Success Rate at 94.8% but is slower than Grok Voice 2.0 on time to first audio, at 0.81 seconds versus 0.70 seconds. It costs $4.80 per hour of input audio, the same as Grok Voice 2.0 and above several rivals.
- Rohan Paul@rohanpaul_aiXGrok Voice 3.0 tops Artificial Analysis speech-to-speech index at 86.9
AIRohan Paul reports that SpaceXAI launched Grok Voice 3.0, which scores 86.9 on Artificial Analysis's Speech-to-Speech Index, ahead of GPT-Live-1 at 83.2. The largest gain is on τ-Voice, where task success rose from 56.5% under Grok Voice 2.0 to 71.6%. The post also says Grok is about 40% faster than GPT-Live-1 but costs $0.025 per task, versus $0.030 for GPT-Live-1.
lauren@potetoXGrok Voice 3.0 is a speech-to-speech model that responds in under a secondAISpaceXSI introduces Grok Voice 3.0, which it calls the world's most intelligent speech-to-speech model. It says the model resolves customer calls well, responds in under a second, and costs less than other frontier models. Lauren Tan (@poteto) simply tells users to try it in Grok Bot.