Overview
ElevenLabs Multilingual v2 by ElevenLabs
Eleven Multilingual v2 API is available through a text-to-speech endpoint.
What is Eleven Multilingual v2 API?
ElevenLabs Multilingual v2 delivers natural-sounding text-to-speech in 29 languages with expressive voice cloning.
Technical Specifications
- Supported inputs: Text
- Output: Audio
- Endpoint: /tts
Performance Benchmarks
[embed]
Eleven Multilingual v2 API Pricing
- Input: $234 / 1M tokens
Where to Use Eleven Multilingual v2
Voiceovers and narration
Generate natural speech for videos, courses, and IVR at low per-second cost.
Accessibility and voice agents
Add spoken output to apps, readers, and conversational assistants.
Benchmarks
| Benchmark | Result | Source |
|---|---|---|
| TTS Arena | 1105 (Elo) | artificialanalysis.ai |
Source: Artificial Analysis, retrieved Nov 3, 2026.
Pricing
| Usage | Price | Unit |
|---|---|---|
| Usage | $0.234 | per 1M characters |
Quick start
View docs (opens in a new tab)Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API key (opens in a new tab)export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/tts' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "elevenlabs/eleven_multilingual_v2",
"text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "elevenlabs/eleven_multilingual_v2",
"text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}
response = requests.post("https://api.aimlapi.com/v1/tts", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/tts", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "elevenlabs/eleven_multilingual_v2",
"text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Frequently asked questions
What inputs and outputs does ElevenLabs Multilingual v2 support?
ElevenLabs Multilingual v2 takes text as input and returns audio.
When was ElevenLabs Multilingual v2 released?
ElevenLabs Multilingual v2 became available on January 5, 2026.
Who created ElevenLabs Multilingual v2?
ElevenLabs Multilingual v2 was built by ElevenLabs.
How do I call ElevenLabs Multilingual v2 on AI/ML API?
Send a request to https://api.aimlapi.com/v1/tts with elevenlabs/eleven_multilingual_v2 as the model id.
Is ElevenLabs Multilingual v2 available through a single API key?
Yes. ElevenLabs Multilingual v2 is served through AI/ML API, so the same key and endpoint format used for other models applies.
What languages does ElevenLabs Multilingual v2 support?
It supports text-to-speech generation in 29 languages.
Does ElevenLabs Multilingual v2 support voice cloning?
Yes, it offers expressive voice cloning as part of its text-to-speech generation.
