You can now build text-only conversational agents.
Ideal for:
- Customers that prefer typing to speaking.
- Precise inputs like order IDs or email addresses.
- Solving simple issues, handing off to our voice agents for complex tasks.
Chat Mode is an extension of our Conversational Agent platform, designed to help you reach users in the modality that best fits their context.
ElevenLabs conversational agents are intelligent, real-time AI agents that talk, type, and take action.
Resolve customer issues, automate tasks, and deliver accurate answers - all grounded in your data, tailored to your workflows, and ready to deploy at enterprise scale.
This is the first Music API for developers trained on licensed data and cleared for broad commercial use.
You can now integrate the highest quality AI music into your products and workflows.
Since launch, creators have generated over 750k songs with Eleven Music.
The Eleven Music API allows you to:
- Generate high quality tracks from text prompts
- Create vocal or instrumental versions in any genre
- Customize length, structure, and language
Created in collaboration with labels, publishers, and artists, songs created with the Eleven Music API are available for broad commercial use.
It’s designed for building apps across media and entertainment. Whether you’re delivering personalized mediations, producing music for video games, or creating AI generated ads.
Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever.
Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers].
Now in public alpha and 80% off in June.
This is a research preview. It requires more prompt engineering than previous models - but the generations are breathtaking.
We’ll continue fine-tuning to improve reliability and control.
The new architecture of Eleven v3 deeply understands text - delivering much greater expressiveness.
And now you can guide generations more directly using audio tags:
- Emotions [sad] [angry] [happily]
- Delivery direction [whispers] [shouts]
- Non-verbal reactions [laughs] [clears throat] [sighs]
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.