Skip to content
Dashboard

Grok STT

Transcribe audio to text in 25 languages with batch and streaming modes.

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
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
256K
0.4s
191tps
$1.00/M
$2.00/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+3
xai logo
05/20/2026
1M
1.1s
99tps
$1.25/M
$2.50/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+4
vertex logo
xai logo
04/30/2026
2M
0.4s
147tps
$1.25/M
$2.50/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+3
vertex logo
xai logo
03/09/2026
2M
1.4s
$1.25/M
$2.50/M
Read:
$0.2/M
Write:
$5/K
+ input costs
+4
xai logo
03/09/2026
1M
0.3s
158tps
$0.20/M$0.50/M
Read:$0.05/M
Write:
+2
vertex logo
07/09/2025
1M
0.8s
208tps
$0.20/M$0.50/M
Read:$0.05/M
Write:
+3
vertex logo
07/09/2025