ElevenLabs Multilingual v2
ElevenLabs Multilingual v2 is ElevenLabs' consistency-first text-to-speech model, covering 29 languages with stable, faithful delivery from take to take. It reproduces a speaker's identity rather than improvising a performance, which makes it the right renderer for cloned and designed voices. Choose it for narration, audiobooks, and any work where a voice must stay exactly itself; choose ElevenLabs v3 when you want expressive acting with audio tags instead.
Pricing
Input
$0.120 / min
Output
—
Pay only for what you use. No subscriptions, no minimums.
Specs
- Context
- —
- Max output
- —
- Latency
- Fast
- Category
- Audio
- Arabic
- Partial
Constraints & limits
Max input
Per provider
Output
MP3 (32 kHz, 128 kbps, mono)
The gateway auto-clamps requests to the model's limits where possible.
Quick start
This sample hits the text-to-speech endpoint. Change base_url and your key, then run it.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.audio.speech.create(
model="elevenlabs/eleven-multilingual-v2",
input="Welcome to Thalam, your unified gateway to AI models.",
)
with open("out.mp3", "wb") as f:
f.write(response.content)Similar models
ElevenLabs v3
ElevenLabs v3 — gold-standard voice synthesis.
Fish Audio TTS
Fish Audio TTS — multilingual voice synthesis with cloning.