ElevenLabs
Eleven Multilingual v3
ElevenLabs’ multilingual TTS flagship — 70+ languages, emotional audio tags and ultra-low latency.
Intelligence
94.0 #4
AAQI 94.0
Output Speed
200 t/s
ITL 5.0 ms/tok
Blended price (3:1)
$0.03 /1M
In $0.025/M · Out $0.05/M
Context
32K
≈ 80 A4 pages · max out 8,192
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Eleven Multilingual v3
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.
Strengths & Trade-offs
Where it wins
- Best-in-class emotional range and prosody
- Ultra-low latency for real-time voice agents
- Broadcast-quality multi-speaker scenes
- 70+ languages on one voice
Trade-offs to watch
- Premium per-character pricing
- Audio tags need prompt-side tuning
- Closed API — no self-hosting
Killer Use Cases
Voice agents & IVR
Expressive sub-100ms spoken turns.
Audiobook & dubbing
Multi-speaker long-form narration.
Game dialogue
Dynamic NPC speech with emotional tags.
Developer Quickstart & API
Set
ELEVENLABS_API_KEY first — get an API keycurl -X POST "https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID" \
-H "xi-api-key: $ELEVENLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text": "Welcome to the future of voice agents.", "model_id": "eleven_v3"}' \
--output speech.mp3import os, requests
resp = requests.post(
"https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID",
headers={"xi-api-key": os.environ["ELEVENLABS_API_KEY"]},
json={"text": "Welcome to the future of voice agents.", "model_id": "eleven_v3"},
)
open("speech.mp3", "wb").write(resp.content)const res = await fetch("https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID", {
method: "POST",
headers: { "xi-api-key": process.env.ELEVENLABS_API_KEY, "Content-Type": "application/json" },
body: JSON.stringify({ text: "Welcome to the future of voice agents.", model_id: "eleven_v3" }),
});
await fs.promises.writeFile("speech.mp3", Buffer.from(await res.arrayBuffer()));Text-to-speech — replace VOICE_ID with a voice from your library; returns an audio stream.
Official Resources & Links
API deployment
Compare hosts & latency
Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Groq
Cerebras
Together AI
DeepInfra
Fireworks AI
AWS Bedrock
Azure AIScores by Source
Category Scores
Benchmark Results
Head-to-head Live Matchups
Voxtral 3 TTS+3.8
Qwen Audio 3.1 TTS++4.6
Claude Mythos Preview-3.4
Kimi K3.1 Pro-0.2Live Specs & Architecture
Under the hood
Eleven v3 — multilingual speech synthesis
- 70+ languages with cross-lingual voice transfer
- Inline audio tags — [laughs], [whispers], dramatic pauses
- Sub-80ms streaming TTFT for live agents
- Studio-grade multi-speaker dialogue mode
Release date
Oct 22, 2026
Architecture
Eleven v3 — multilingual speech synthesis
Parameters
Not disclosed
License
Proprietary
Context Window
32,000 tokens
Max Output
8,192 tokens
Modalities
text + audio
Cache Pricing
read $0.008 · write $0.03 /1M
Reasoning
—
Input Price
$0.025/M
Output Price
$0.05/M
Output Speed
200 t/s
Time to First Token
—
Data Updated
Oct 22, 2026
Estimated monthly bill
Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...
Cite & embed
GitHub Markdown badge
Loading badge markdown...BibTeX
@misc{llmpodium2026elevenv3,
title = {Benchmark Analysis and Intelligence Evaluation of Eleven Multilingual v3},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/eleven-v3}
}Embed Score Badge
Add a live Podium Score badge to your GitHub or Hugging Face README — it links back to the live ranking.
Preview
Markdown
Loading badge snippet...HTML
Loading badge snippet...More from ElevenLabs
Alternative Models
Closest alternatives to Eleven Multilingual v3 based on capabilities, pricing, and benchmark scores.
