Introducing New Modalities

Agents built on ElevenAgents can now take images, PDFs and audio from customers on WhatsApp and the web widget and keep context across channels. Document-driven flows such as proof of address or claims no longer need a form or human handoff.

• multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

• articleUnpacking Elevenagents Orchestration Engine
• articleElevenlabs Is Now A Kiro Power
• articleWebinar Recap Build Safe Ai Agents For An Enterprise Deployment
• articleProcessing Images And Documents In Elevenagents

• articleProcessing Images And Documents In ElevenagentsElevenLabs editorial sitemap
• article👀 Seeing is just the beginning. With Qwen-MM-Plugins, turn your favorite agent Alibaba_Qwen
• articleIntroducing Voice Music Image And Video Generation In The Elevenlabs McpElevenLabs editorial sitemap

Checking sign-in…

Loading comments…