TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Models
Eleven Multilingual

Eleven Multilingual

By Eleven Labs
New Audio Gen 3
Released: August 23, 2023

Overview

Description

Flagship model (v2) for lifelike, emotionally rich speech synthesis in 29 languages; Maintains speaker’s voice characteristics and accent across languages. Use cases: audiobooks, character voiceovers, professional content.

About Eleven Labs

No company description available.

Industry: Research Services
Company Size: 11-50
Location: Warsaw, New York, US
Website: elevenlabs.io
View Company Profile

Related Models

Hailuo Audio 01 music

Hailuo Audio 01 music is an earlier music generation model for hooks, riffs, and ambient beds.

Audio New

Amazon Nova Sonic

Amazon Nova Sonic is a real-time, speech-first model in the Nova family. It streams speech-to-text, reasons while you’re talking, and speaks back instantly—enabling natural, interruptible voice agents on web and mobile.

Audio New

Doubao Realtime Voice

Doubao Realtime Voice is ByteDance’s low-latency voice interface for the Doubao models—streaming speech-to-text, LLM reasoning, and text-to-speech in a single session so agents can talk naturally, interrupt mid-sentence, and respond instantly on web or mobile.

Audio New
Last updated: October 8, 2025