ElevenLabs voice agents now handle images, PDFs, and location pins
On WhatsApp and web, ElevenAgents can process photos, documents, contacts, and location pins alongside voice and chat.
On WhatsApp, ElevenLabs' ElevenAgents can now process images, PDFs, audio messages, contacts, and location pins, in addition to voice and chat. A customer can send a photo of their router, and the agent reads the indicator lights, runs a line check, and books an engineer visit without human intervention.
In the web widget, customers can now upload images and PDFs directly alongside voice and chat, so proof of address, medical records, or claim documents get processed in the same conversation instead of being routed to a form, an email thread, or a human queue.
Agents keep context across channels and modalities within one conversation: an agent on a voice call can send a WhatsApp message to share a quote or confirm an appointment, then process a signed PDF sent back, without the customer repeating themselves. The new modalities are available now on top of the existing voice and chat experiences on web, in-app, WhatsApp, and telephony, described in the announcement.
