Steady in 29 languages.
IllustrationA voice that sounds the same from the first paragraph to the last.
Explainers
Clear, measured narration over product demos.
Courses
Lesson audio that stays consistent across modules.
Audio articles
Blog posts and newsletters as listenable audio.
- Provider
- ElevenLabs
- Voices
- 21 stock voices
- Languages
- 29, or automatic detection
- Speed
- 0.7 to 1.2
- Controls
- Stability, similarity, style
- Plans
- Hobby and up
- Cost
- 17 credits per 1,000 characters
What is ElevenLabs Multilingual v2?
ElevenLabs Multilingual v2 is ElevenLabs' text to speech model for consistent, natural narration. It reads in 21 voices across 29 languages, and exposes fine controls: speed from 0.7 to 1.2, stability, similarity to the original voice, and style exaggeration. Where v3 is built for performance, Multilingual v2 is built for long, even reads that sound the same from the first paragraph to the last. On APImage it costs 17 credits per 1,000 characters.
How much does Multilingual v2 cost?
17 credits per 1,000 characters.
Multilingual v2 or v3?
v3 for expressive, directed performances. Multilingual v2 for stable, controllable narration.
Which plan includes it?
Hobby and up.
How do I use it?
Open the Audio studio, choose Text to speech and pick Multilingual v2. Pick a voice and the language, or leave it on auto. Set speed and stability, and paste the script. Generate.