Models
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 ID | Description | Max Characters | Languages | Best For |
|---|---|---|---|---|
eleven_multilingual_v2 | Most life-like, emotionally rich model | 10,000 | 29 languages | Voice overs, audiobooks, content creation |
eleven_turbo_v2_5 | High quality, low-latency model | 40,000 | 32 languages | Developer use cases requiring speed and multiple languages |
eleven_turbo_v2 | High quality, low-latency model | 30,000 | English only | Developer use cases requiring speed (English only) |
eleven_english_sts_v2 | State-of-the-art speech-to-speech | 5,000 | English only | Maximum control over content and prosody |
eleven_multilingual_sts_v2 | Cutting-edge multilingual speech-to-speech | 10,000 | 29 languages | Advanced multilingual speech synthesis with prosody control |
Model Selection Guide
Choose your model based on these primary considerations:
Latency Requirements
• Quality over Speed? Use Standard Multilingual models
• Need
real-time? Use Turbo models
Language Support
• English only? → Consider eleven_turbo_v2
• Multiple
languages? → Use eleven_multilingual_v2 or eleven_turbo_v2_5
Use Case
• Content Creation → eleven_multilingual_v2
• Conversational AI
→ eleven_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.
Was this page helpful?