Eleven Multilingual V2
Neural Network
Eleven Multilingual V2 is an ElevenLabs speech synthesis model for vivid, emotional voiceovers in 29 languages.
Specifications
- Input
- text
- Output
- audio
- Number of voices
- 6
Prompt cost
(per 1M tokens)
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
import fs from 'fs';
async function main() {
const response = await openai.audio.speech.create({
model: 'eleven_multilingual_v2',
voice: 'nova',
input: 'Hello! This is a speech generation example via BotHub.',
response_format: 'mp3',
speed: 0.9
});
const buffer = Buffer.from(await response.arrayBuffer());
await fs.promises.writeFile('output.mp3', buffer);
}main();
How it works Eleven Multilingual V2?
Eleven Multilingual V2 is a speech synthesis model from ElevenLabs designed for natural sound and emotional expression. It supports 29 languages, allowing you to voice a single role for different markets while maintaining the voice's character. The vendor positions it for voiceovers, audiobooks, post-production, and any content where human intonation is crucial. In BotHub, the model works without a VPN or foreign card: pay with Russian cards in rubles, only for actual usage, with no subscription, and unused balance does not expire. Over 250 models are available in one window—you can write text for voiceover in a language model and send it directly for synthesis. Requests are encrypted via AES-GCM, and for teams, there is a unified API, contract, invoice, and admin panel with limits. Use it for video and ad voiceovers, audiobooks and podcasts, educational course voices, dubbing and video localization, or to replace voiceover recordings during editing.Frequently asked questions about Eleven Multilingual V2
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
This is a speech synthesis model from ElevenLabs: you provide text, and you get an audio track as output. It is suitable for voicing videos and reels, podcasts, audio versions of articles and books, educational courses, voice responses in services, and voice interface prototypes.
You get audio as output—synthesized speech based on the submitted text. For a single request, the model works with up to 10,000 tokens, so it is more convenient to split long materials into parts. Exact file parameters depend on the access method: via the BotHub interface or API.
A step-by-step reasoning mode is not noted in our data—that is not its task. The model specializes in text-to-speech, not logic and analysis. If reasoning is needed, prepare a script using a text model in the same BotHub window and send the finished text for synthesis.
Function calling and structured output are not noted for this model in our data. However, it is available via the unified OpenAI-compatible BotHub API, so you can integrate speech synthesis into your pipeline as a separate step—alongside text models that do support such functions.
Accepting files other than text is not noted in our data: the main scenario is to send text and receive an audio track. If you need to voice a document, first extract the text from it, and for analyzing images or videos, use multimodal models in the same interface.
The model belongs to the ElevenLabs multilingual line, but the exact list of supported languages is not specified in our data. Therefore, it is most reliable to test the sound with a short fragment of your text: in BotHub, you pay only for actual usage, without a subscription.