Skip to content
Dashboard

Grok STT

Grok STT is xAI's speech-to-text model. It transcribes recorded audio into text across 25 languages, available through Vercel AI Gateway with the AI SDK.

index.ts
import { experimental_transcribe as transcribe } from 'ai';
import { gateway } from '@ai-sdk/gateway';
import { readFile } from 'node:fs/promises';
const result = await transcribe({
model: gateway.transcriptionModel('xai/grok-stt'),
audio: await readFile('audio.mp3'),
});

More models by xAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
500K
1.3s
134tps
$2/M
$6/M
Read:
$0.5/M
Write:
$5/K
+ input costs
+3
xai logo
07/08/2026
1M
0.7s
119tps
$1.25/M
$2.50/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+3
vertex logo
xai logo
04/30/2026
2M
0.3s
90tps
$1.25/M
$2.50/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+2
vertex logo
xai logo
03/10/2026
2M
0.5s
195tps
$1.25/M
$2.50/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+3
vertex logo
xai logo
03/10/2026
1M
0.3s
165tps
$0.20/M
$0.50/M
Read:$0.05/M
Write:
+1
vertex logo
11/19/2025
1M
1.0s
175tps
$0.20/M
$0.50/M
Read:$0.05/M
Write:
+2
vertex logo
11/19/2025