Eleven Multilingual v2
eleven_multilingual_v2
Our most life-like, emotionally rich mode in 29 languages. Best for voice overs, audiobooks, post-production, or any other content creation needs
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| voice_id *声音id | text | — | — | |
| language_codeISO 639-1语言code | text | — | — | |
| similarity_boostSimilarity Boost | slider | 0.75 | 0 ~ 1 · step 0.05 | |
| stabilityStability | slider | 0.5 | 0 ~ 1 · step 0.05 |
Output fields
| Field | Type | Description |
|---|---|---|
| audio_url | string |
API
Call this model through one unified REST API. Get a key on the API Keys page.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/eleven_multilingual_v2" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"voice_id": "JBFqnCBsd6RMkjVDRZzb",
"language_code": "en",
"similarity_boost": 0.8,
"stability": 0.55
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/eleven_multilingual_v2",
headers=HEADERS,
json={
"input": {
"voice_id": "JBFqnCBsd6RMkjVDRZzb",
"language_code": "en",
"similarity_boost": 0.8,
"stability": 0.55
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/eleven_multilingual_v2", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"voice_id": "JBFqnCBsd6RMkjVDRZzb",
"language_code": "en",
"similarity_boost": 0.8,
"stability": 0.55
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);Documentation
Multilingual V2
A high-naturalness multilingual text-to-speech model built for fast, reliable, and cost-efficient voice generation.
Multilingual V2 is ElevenLabs’ multilingual text-to-speech model for converting written text into clear, expressive speech. It combines natural prosody, strong multilingual performance, no cold starts, and affordable character-based pricing, making it a practical choice for both real-time and production-scale audio generation.
🚀 Key Features
- High naturalness: Produces humanlike intonation, pacing, and timing for polished voice output.
- Multilingual support: Optimized for multilingual synthesis with improved pronunciation and accent handling.
- Tunable voice delivery: Adjust
similarityandstabilityto balance speaker likeness, clarity, and consistency. - Speaker Boost for English normalization: Improves reading quality for numbers, dates, units, and similar structured content.
- No cold starts: Well suited for interactive applications and high-frequency workloads.
- Affordable pricing: Simple per-character pricing supports predictable cost control from prototyping to production.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Multilingual text-to-speech(TTS) |
| Model ID | elevenlabs/multilingual-v2 |
| Input | Text(string) |
| Output | Audio |
| Maximum input length | 10,000 characters |
| Billing unit | 1 character = 1 token; charged per character |
| Voice selection | voice_id, default Alice; supports built-in and custom voices |
| Similarity control | similarity: 0.0–1.0, default 1 |
| Stability control | stability: 0.0–1.0, default 0.5 |
| English normalization boost | use_speaker_boost: boolean, default true |
| Pause control | Use <#x#> between words to control pause duration(0.01–99.99s) |
| Latency | No fixed public value provided; positioned as no-cold-start, fast inference |
| Typical outputs | Voiceovers, narration, learning content, product videos, customer support audio |
Sample Prompts
Note: This is a text-to-speech model, so the examples below are sample input texts.
Welcome to our product demo. Today we will walk through the key features and benefits in under two minutes.Your order will arrive on Friday <#0.5#> between 2 PM and 5 PM. Thank you for shopping with us.The total balance is 1,245 dollars and 80 cents, due on September 15.
💰 Pricing
| Item | Price |
|---|---|
| Base price | $0.1 / 1,000 characters |
💡 Best Use Cases
- Marketing and branded content: Create polished voiceovers for product demos, ads, and social media videos.
- Education and training: Generate narration for lessons, language learning materials, and internal training content.
- Globalized user experiences: Power multilingual audio for international apps, websites, and customer-facing services.
- Customer support and automated announcements: Especially effective for English content involving numbers, dates, times, and measurements.
🔗 Related Models
- Elevenlabs Multilingual V1: Earlier multilingual version for users comparing legacy output characteristics.
- Elevenlabs Music: A separate model line focused on music-related generation rather than speech synthesis.
Related models
Eleven v3
The most expressive model. Supports 70+ languages. Requires more prompt engineering than our previous models.
Eleven Turbo v2.5
Our high quality, low latency model in 32 languages. Best for developer use cases where speed matters and you need non-English languages.
Eleven Flash v2.5
Our ultra low latency model in 32 languages. Ideal for conversational use cases.