X
XAI / grok-voice-transcribe-2.0

Grok Voice Transcribe 2.0

Second version of xAI’s transcription model for files and live audio.

01 / SUMMARY

The essential

ORIENTATIONSpeech recognition

Primary use stated or inferred cautiously from official documentation.

CONTEXTAudio via file or streaming

Maximum input capacity when published by the source.

EXITTranscription

Documented maximum generation limit.

ACCESSxAI API

Verified availability channels.

MODEL TYPEVoice and audio

Primary functional family and verified specialties.

LICENSEProprietary

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDgrok-voice-transcribe-2.0
Model typeVoice and audio
Access modelPaid proprietary
LicenseProprietary
DeploymentHosted API
Release17 SEP 2026
Knowledge cutoffNot published
EntranceAudio
ExitText
Context windowAudio via file or streaming
maximum outputTranscription
ReasoningNot published
Published toolsTranscription · Timestamps
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningNot published
Verified platformsxAI API
BEST SUITED FOR

Multilingual transcription and subtitling with timestamps.

WORTH MONITORING

Evaluate accuracy by language, accent, noise, and custom vocabulary.

03 / CAPABILITIES

What it can do

01

Orientation

Multilingual transcription and subtitling with timestamps.

02

Context

Audio via file or streaming · Transcription

03

Tools and integration

Transcription · Timestamps

04

Access

xAI API

Input modalities
Audio
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNot publishedStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputNot publishedMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

Consult the primary source before budgeting for a deployment.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.

i We have not found published benchmarks for this model.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

Grok Voice Transcribe 2.0

Version added to Inferama's verified catalog.

07 / SOURCES

Traceability