Eleven v4
ElevenLabs' expressive text-to-speech model with audio tags for emotion and delivery, multilingual speech, and multi-speaker dialogue support. Accepts up to 10,000 characters per request and is billed per input character. Your use is subject to ElevenLabs's Terms & Privacy Policies.
- Input price
- Input $40, Per 1M characters
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('elevenlabs/eleven-v4'), text: 'Hello from the Vercel AI Gateway!', voice: 'hpp4J3VqNfWAUOO0d1Us',});
await writeFile('speech.mp3', result.audio.uint8Array);Copy link to headingPlayground
Try out Eleven v4 by ElevenLabs. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Eleven v4Text
The text the model will read aloud.Voice
Your generated audio will appear here
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Checking availability for your team
| Provider |
|---|
ElevenLabs Legal:Terms•Privacy50% off | $40/M chars | — | 10/27/2026 |
Copy link to headingMore models by ElevenLabs
| Model |
|---|
| — | $2.40/hr | $4.50/M | Read$0.09/M | — | | 10/27/2026 | ||||||||
| — | $2.40/hr | $3/M | Read$0.01/M | — | | 10/27/2026 | ||||||||
| — | $20/M chars | — | | 10/27/2026 | ||||||||||
| — | $20/M chars | — | | 10/27/2026 | ||||||||||
| — | $40/M chars | — | | 10/27/2026 | ||||||||||
| — | $0.08/min | — | | 10/27/2026 |