Multimodal input

Multimodal input settings control extra ways users can send information to the agent beyond speech. They live in the agent's Advanced tab, under Multimodal input.

Let users attach images and PDFs in chat

Collect keypad digits from callers during phone conversations

File input lets users send images and PDFs to the agent in chat. The agent can read those files when the selected model supports image and/or document input.

Users can attach files in the widget, supported chat channels such as Slack, or the upload conversation file API.

Open your agent in the dashboard, confirm the selected model supports image and/or PDF input, then go to the Advanced tab.

Under Multimodal input, turn on Allow file attachments.

Optionally set Files kept in memory and Max files per conversation.

Save the agent. Users can then attach images and PDFs in chat.

elevenlabs agents pull --agent agent_7101k5zvyjhmfg983brhmhkd98n6

Set conversation_config.conversation.file_input:

{
  "conversation_config": {
    "conversation": {
      "file_input": {
        "enabled": true,
        "max_files_in_memory": 10,
        "max_files_per_conversation": 10
      }
    }
  }
}

elevenlabs agents push --agent agent_7101k5zvyjhmfg983brhmhkd98n6

from elevenlabs import ElevenLabs

elevenlabs = ElevenLabs()

elevenlabs.conversational_ai.agents.update(
    agent_id="agent_7101k5zvyjhmfg983brhmhkd98n6",
    conversation_config={
        "conversation": {
            "file_input": {
                "enabled": True,
                "max_files_in_memory": 10,
                "max_files_per_conversation": 10,
            }
        }
    },
)

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";

const elevenlabs = new ElevenLabsClient();

await elevenlabs.conversationalAi.agents.update("agent_7101k5zvyjhmfg983brhmhkd98n6", {
  conversationConfig: {
    conversation: {
      fileInput: {
        enabled: true,
        maxFilesInMemory: 10,
        maxFilesPerConversation: 10,
      },
    },
  },
});

DTMF input lets callers enter digits on their phone keypad during a call. Use it to collect phone numbers, menu choices, and other numeric input without relying on speech recognition.

This is the inverse of the play keypad touch tone system tool, which sends tones from the agent.

Each keypad press is buffered until the sequence is complete. Completing a sequence creates one user turn.

1. The caller presses a key. The first digit interrupts the agent if it is speaking.
2. Further digits append to the same buffer.
3. The sequence completes when the caller presses # (if hash termination is enabled) or when no further digits arrive before the timeout.
4. The agent receives the collected digits as a user turn and responds.

# is a terminator when hash termination is enabled; it is not included in the collected string. A # pressed with an empty buffer is ignored. The buffer accepts 0-9, *, #, and A-D, up to 50 characters.

conversation_config.conversation.dtmf_input_settings is null when DTMF input is disabled. When enabled, the defaults are:

Redaction applies to the keypad turn in stored conversation data. It does not hide digits from the agent during the live call, and it does not rewrite digits the agent speaks back or sends to a tool. That is separate from conversation history redaction.

Open your agent in the dashboard and go to the Advanced tab.

Under Multimodal input, turn on Enable DTMF input.

Optionally set DTMF input timeout, Use # to complete DTMF input, and Redact DTMF input.

Save the agent, then place a phone call and enter digits on the keypad.

elevenlabs agents pull --agent agent_7101k5zvyjhmfg983brhmhkd98n6

Set conversation_config.conversation.dtmf_input_settings. Omit the object, or set it to null, to disable DTMF input.

{
  "conversation_config": {
    "conversation": {
      "dtmf_input_settings": {
        "dtmf_input_timeout": 2.0,
        "hash_terminator": true,
        "redact_input": false
      }
    }
  }
}

elevenlabs agents push --agent agent_7101k5zvyjhmfg983brhmhkd98n6

from elevenlabs import ElevenLabs

elevenlabs = ElevenLabs()

elevenlabs.conversational_ai.agents.update(
    agent_id="agent_7101k5zvyjhmfg983brhmhkd98n6",
    conversation_config={
        "conversation": {
            "dtmf_input_settings": {
                "dtmf_input_timeout": 2.0,
                "hash_terminator": True,
                "redact_input": False,
            }
        }
    },
)

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";

const elevenlabs = new ElevenLabsClient();

await elevenlabs.conversationalAi.agents.update("agent_7101k5zvyjhmfg983brhmhkd98n6", {
  conversationConfig: {
    conversation: {
      dtmfInputSettings: {
        dtmfInputTimeout: 2.0,
        hashTerminator: true,
        redactInput: false,
      },
    },
  },
});

Update the agent's system prompt so it knows when to ask for keypad input. For example:

If you need the caller's phone number, ask them to type it on their keypad. Wait for the DTMF
input before continuing.