Note: eleven_v3 is in alpha, expect to generate multiple takes.
We're thrilled to announce the integration of the ElevenLabs v3 model into our platform, bringing significant upgrades to audio quality and performance.
What’s New with ElevenLabs v3
- Improved Voice Quality: Enjoy even more natural, expressive, and lifelike speech synthesis. The v3 model delivers clearer intonation, pacing, and pronunciation for all voices.
- Greater Language Support: Expanded support for more languages and dialects, broadening the reach of your video content.
- Consistent Audio Experience: Enhanced consistency across different AI-generated clips for a smoother listening experience.
- Smarter Voice Customization: Advanced controls for tuning emotion, tone, and inflection, helping your videos better match your brand and messaging.
How It Works
Before we automatically use the v3 model, you can enable it in the voiceover settings.
How to enable the v3 model
- Go to the video editor
- Click on the voiceover settings
- Enable the v3 model
- Click on the generate voiceover button
- Enjoy the improved audio quality