Introducing Grok Voice Think Fast 2.0
xAI announced Grok Voice Think Fast 2.0, a speech-to-speech voice model with improved transcription accuracy and efficiency, priced at $0.08 per minute.
- Grok Voice Think Fast 2.0 shows 1.5–2.0× improvement in transcription accuracy over Deepgram Nova 3 and ElevenLabs Scribe v2, and 1.4× over its predecessor.
- The model reasons while speaking, enabling tool calls to execute before the agent finishes its first sentence.
- It is trained to speak in shorter sentences, ask one question at a time, and avoid fluff, improving conversational flow.
- On August 5, 2026, grok-voice-latest will switch to this model; users can pin the old version to stay on it.
- Pricing is $0.08 per minute of audio.
Developers and businesses using xAI's voice models will get better accuracy and efficiency without prompt changes, potentially improving conversion and support metrics.
Sources
Read this as text
Back to the AI news