All models
Voice & realtimeStable
SpaceXAI
Grok Voice Think Fast 2.0
SpaceXAI's current realtime speech-to-speech model for sub-second conversational agents with tool access.
Plain-English overview
What Grok Voice Think Fast 2.0 actually is
Grok Voice Think Fast 2.0 powers the current grok-voice-latest route and combines realtime speech with agent tool use. The provider publishes a per-audio-minute price, making it easier to estimate calls than token-only audio pricing.
The sub-second label is a provider-level claim, not a guaranteed mouth-to-ear measurement. Telephony, network distance, voice activity detection, tool calls, and application logic all affect the user's experience.
Good fit for
- Realtime voice agents with tools
- Minute-based call-cost planning
- Teams using SpaceXAI's model and search stack
Category comparison
The facts that matter for voice models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Price basisToken-, character-, or minute-based price for the listed access route.
- $0.08 / audio minute
- Interaction modeSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.
- Realtime speech-to-speech with tools
- Published latencyProvider-published measurement with its stated exclusions; not a Cody test.
- Sub-second provider claim
- LanguagesProvider-documented language coverage or a clear unpublished marker.
- Exact supported list not published here
- Tools & controlNative function calling, reasoning, or speech-control features.
- Realtime tool use
- Context or input limitDocumented token or character limit where it is meaningful.
- Not published
API and provider access
Where to get Grok Voice Think Fast 2.0
Availability
Regions and access stage
Available through the SpaceXAI Realtime API; the grok-voice-latest alias routes to this model from August 5, 2026.
Account and regional availability should be verified in the SpaceXAI console.
Check live availabilityData and training
The route matters.
SpaceXAI says it does not train on API inputs or outputs without explicit permission. Default encrypted retention is 30 days; team-level zero data retention is available with feature tradeoffs.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Grok Voice Think Fast 2.0 FAQ
What is Grok Voice Think Fast 2.0?
SpaceXAI's current realtime speech-to-speech model for sub-second conversational agents with tool access. Grok Voice Think Fast 2.0 powers the current grok-voice-latest route and combines realtime speech with agent tool use. The provider publishes a per-audio-minute price, making it easier to estimate calls than token-only audio pricing.
When was Grok Voice Think Fast 2.0 released?
Grok Voice Think Fast 2.0 was released on July 29, 2026 according to the cited provider materials.
Where can I access Grok Voice Think Fast 2.0?
Available through the SpaceXAI Realtime API; the grok-voice-latest alias routes to this model from August 5, 2026. The access routes listed in this guide are SpaceXAI, SpaceXAI.
How much does Grok Voice Think Fast 2.0 cost?
$0.08 / audio minute. SpaceXAI lists speech-to-speech audio at $0.08/minute plus $0.004 per text input unit shown on its pricing page.
Where is Grok Voice Think Fast 2.0 available?
Available through the SpaceXAI Realtime API; the grok-voice-latest alias routes to this model from August 5, 2026. Account and regional availability should be verified in the SpaceXAI console.
Is my Grok Voice Think Fast 2.0 API data used for training?
SpaceXAI says it does not train on API inputs or outputs without explicit permission. Default encrypted retention is 30 days; team-level zero data retention is available with feature tradeoffs. The policy belongs to the provider route and account terms, so verify it again before production use.
Research trail
Sources for this guide
Keep comparing
More voice & realtime models
OpenAI · Stable
GPT-Realtime-2.1
OpenAI's realtime speech-to-speech reasoning model for tool-using voice agents that also need text and image context.
Read guideGoogle · Preview
Gemini 3.1 Flash Live Preview
Google's preview audio-to-audio model for low-latency dialogue with multimodal awareness, thinking, search grounding, and function calling.
Read guideElevenLabs · Stable
Eleven v3 Conversational
ElevenLabs' expressive realtime text-to-speech model for natural dialogue, emotional delivery, audio tags, and more than 70 languages.
Read guide