Eleven Multilingual v2
Multilingual v2 marked ElevenLabs’ exit from beta in August 2023. It expanded speech synthesis and voice cloning to a much broader language set than the original multilingual release.
Narration across languages
The launch connected the new model with Professional Voice Cloning. A voice could speak several supported languages rather than requiring a separate recording for each one. Current documentation still identifies this model as a stable choice for long-form generation.ElevenLabs: Multilingual v2 release and end of betaElevenLabs API introduction and model specifications
Practical guidance. Evaluate a complete chapter when choosing this model for narration. A newer model’s stronger emotional range does not by itself establish better consistency for a particular narrator.ElevenLabs API introduction and model specifications
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | API, Provider product |
| Model identifiers | eleven_multilingual_v2 |
| Current coverage | 29 languagesElevenLabs API introduction and model specifications |
| Input limit | 10,000 characters per requestElevenLabs API introduction and model specifications |
Related models
- Eleven v4
ElevenLabs · Eleven speech
Speech model for expressive narration, consistent character voices and multi-speaker dialogue.
Launch date API · Provider product - Eleven Flash v2.5
ElevenLabs · Eleven Flash
Multilingual speech model designed for short response delays.
Launch date API · Provider product - Eleven Multilingual v1
ElevenLabs · Eleven speech
Retired first multilingual speech model, covering English and seven additional languages.
Launch date RetiredAPI · Provider product