Skip to content

Introducing new modalities for ElevenAgents

One agent, every channel, every modality.

new modalities

ElevenAgents already handles voice and chat conversations across web, in-app, phone lines and WhatsApp. But customer requests often require more to complete end-to-end. Setting up a new bank account requires proof of address. An insurance claim needs evidence. A healthcare appointment needs medical records.

With new modalities for ElevenAgents, agents now process images, files, audio notes, contacts, and locations, enabling more issues to be resolved end-to-end.

WhatsApp: images, files, audio, contacts, and locations

On top of voice and chat, ElevenAgents now processes images, PDFs, audio messages, contacts, and location pins on WhatsApp. 

A customer says "my wifi keeps dropping" and sends a photo of their router. The agent reads the indicator lights, runs a line check, and books an engineer visit - all with no human intervention

whatsapp

Rohlik, one of Europe's largest online grocery platforms serving over 3 million e-grocery customers, runs WhatsApp as a primary support channel across five markets. Their agent, Maia, handles customer requests in six languages and handles more than 30 distinct actions - from checking real-time order status to issuing credits.

Web widget: file and image uploads

On your website or app, customers can upload images and PDFs directly in the widget, alongside voice and chat. Proof of address, medical records, insurance claim documents - the agent processes the file and resolves the issue in the same conversation, without bouncing the customer to a form, an email thread, or a human queue.

file widget

Cross-channel context

Agents maintain full context across channels and modalities. The conversation is one continuous thread, even when the channel and modality change.

For example, an agent on a voice call can send a WhatsApp message mid-conversation to share a quote or confirm an appointment, then process the customer's signed PDF when it comes back - all in the same interaction. The customer doesn't repeat themselves, and the agent doesn't lose context.

side by side

One agent, every channel, every modality

New modalities are available now in ElevenAgents, on top of the voice and chat experiences customers already deploy on web, in-app, WhatsApp, and telephony. Meet your customers in the channel and the format they choose, and resolve the issue in one conversation.

Learn more: WhatsApp docs and widget docs.

Explore articles by the ElevenLabs team

Create with the highest quality AI Audio