
Eleven v3 Audio Tags: Precision delivery control for AI speech
Fine-grained control over timing, rhythm, and emphasis with Eleven v3 Audio Tags. Transform flat delivery into dynamic, performative content.
Introducing Eleven v3 (alpha)
Try v3A breakthrough in human-dog communication thanks to AI.
Here at ElevenLabs, we introduced the world's first ultra-realistic Text to Speech model, and recently launched the world's most accurate Speech to Text model, Scribe.
But we're not stopping there.
Today, we're taking one small step for man, and one giant leap for man's best friend.
Introducing Text to Bark, the world's first AI-powered TTS model for dogs.
Simply type a message, choose your breed, and our models will convert it into fluent barking.
Independent benchmarking shows that 95% of dogs couldn't distinguish between ElevenLabs AI-generated barks and real ones, a result that got tails wagging among the international AI community.
Underpinned by a backbone of open-source canine linguistic research, we're proud to be pioneering a new era of cross-species communication.
Business customers will be pleased to hear that Text to Bark is launching with enterprise-grade security and 2FP (2-Factor Pawthentication) as standard. TTB can be deployed from all major cloud barkitecture providers.
Happy barking.
Fine-grained control over timing, rhythm, and emphasis with Eleven v3 Audio Tags. Transform flat delivery into dynamic, performative content.
Create dynamic multi-character dialogue with Eleven v3 Audio Tags. Script overlapping voices, interruptions, and emotional shifts for natural, human-like AI conversations.