Back to models

grok-voice-transcribe-2.0

xAI · ASR

Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming

Model ID xai/grok-voice-transcribe-2.0Updated Sep 17, 2026

Pricing & billing

Billing unit: second. Vendor reference price; conversion is approximate.

ItemUSD referenceList price (USD)
Input—No public pricing—No public pricing
Output$0.000028$0.000028
Cache read—No public pricing—No public pricing
Cache write—No public pricing—No public pricing

Specifications

Form
Speech-to-text
Input modalities
Audio
Output modalities
Text
Weights
Closed
Family
grok
Released
Sep 17, 2026

Uses and capabilities

Capabilities Speech-to-text

Function calling

Structured output

Reasoning

Prompt caching

Open weights

Sources

Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.