Skip to content
Dashboard

Grok TTS

Grok TTS is xAI's text-to-speech model with five expressive voices, speech tags, and telephony codec support, available through Vercel AI Gateway.

index.ts
import { experimental_generateSpeech as generateSpeech } from 'ai';
import { gateway } from '@ai-sdk/gateway';
import { writeFile } from 'node:fs/promises';
const result = await generateSpeech({
model: gateway.speechModel('xai/grok-tts'),
text: 'Hello from the Vercel AI Gateway!',
voice: 'eve',
});
await writeFile('speech.mp3', result.audio.uint8Array);

More models by xAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
500K
1.3s
142tps
$2/M
$6/M
Read:
$0.5/M
Write:
$5/K
+ input costs
+3
xai logo
07/08/2026
1M
0.6s
123tps
$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
100tps
$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
204tps
$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
154tps
$0.20/M
$0.50/M
Read:$0.05/M
Write:
+1
vertex logo
11/19/2025
1M
1.0s
126tps
$0.20/M
$0.50/M
Read:$0.05/M
Write:
+2
vertex logo
11/19/2025