ElevenLabs is the leading provider of AI-powered audio technology. This guide helps developers choose the right model for their use case.

Eleven Multilingual v2

Our most advanced speech synthesis model.


Highest realism, emotional range

Best for voiceovers, audiobooks, content

Eleven Turbo v2.5

High quality, low latency Turbo model


Ultra-low latency (~300ms)

Ideal for real-time, multi-language AI

Flagship Models

Model IDDescriptionMax CharactersLanguagesBest For
eleven_multilingual_v2Most life-like, emotionally rich model10,00029 languagesVoice overs, audiobooks, content creation
eleven_turbo_v2_5High quality, low-latency model40,00032 languagesDeveloper use cases requiring speed and multiple languages
eleven_turbo_v2High quality, low-latency model30,000English onlyDeveloper use cases requiring speed (English only)
eleven_english_sts_v2State-of-the-art speech-to-speech5,000English onlyMaximum control over content and prosody
eleven_multilingual_sts_v2Cutting-edge multilingual speech-to-speech10,00029 languagesAdvanced multilingual speech synthesis with prosody control

Model Selection Guide

Choose your model based on these primary considerations:

1

Latency Requirements

Quality over Speed? Use Standard Multilingual models
Need real-time? Use Turbo models

2

Language Support

English only? → Consider eleven_turbo_v2
Multiple languages? → Use eleven_multilingual_v2 or eleven_turbo_v2_5

3

Use Case

Content Creationeleven_multilingual_v2
Conversational AIeleven_turbo_v2_5
Professional Voice Clones → Either model
Speech to Speech?eleven_english_sts_v2 or eleven_multilingual_sts_v2 family

For detailed language support information and troubleshooting guidance, refer to our help documentation.