Audio environment

Audio environment controls how the agent's outbound audio sounds to the caller. Two settings apply:

• Background sound plays a looping ambient sound under agent speech.
• Voice filter applies a phone-style filter to the agent's voice before that mix.

The caller hears the result. The agent does not hear the background sound, and it is not sent into speech recognition.

This is separate from tool call sounds, which play only while a tool runs.

Background sound mixes a built-in preset under agent speech for the duration of the conversation. The sound keeps looping when the user interrupts; it does not stop with the agent's turn.

Presets include office, restaurant, city, typing, and elevator music. In the dashboard, you can preview a preset before you save.

Configure background sound with conversation_config.conversation.background_sound.

Open your agent. On the Agent page, next to Voices, click the Audio environment button.

Turn on Enable background sound. Choose a preset from Background sound. Use the play control next to the dropdown to preview it.

Set Volume. Keep Crossfade loop enabled to avoid an audible click when the sound repeats. Save your changes.

elevenlabs agents pull --agent agent_7101k5zvyjhmfg983brhmhkd98n6

Set conversation_config.conversation.background_sound. Valid source_id values are office1, office2, restaurant, city, typing, and elevator1 through elevator4.

{
  "conversation_config": {
    "conversation": {
      "background_sound": {
        "source_type": "preset",
        "source_id": "office2",
        "volume": 0.15,
        "crossfade_loop": true
      }
    }
  }
}

To disable background sound, set source_type and source_id to null. Do not omit background_sound or set the object to null; an update keeps the existing setting.

elevenlabs agents push --agent agent_7101k5zvyjhmfg983brhmhkd98n6

from elevenlabs import ElevenLabs

elevenlabs = ElevenLabs()

elevenlabs.conversational_ai.agents.update(
    agent_id="agent_7101k5zvyjhmfg983brhmhkd98n6",
    conversation_config={
        "conversation": {
            "background_sound": {
                "source_type": "preset",
                "source_id": "office2",
                "volume": 0.15,
                "crossfade_loop": True,
            }
        }
    },
)

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

const elevenlabs = new ElevenLabsClient();

await elevenlabs.conversationalAi.agents.update("agent_7101k5zvyjhmfg983brhmhkd98n6", {
  conversationConfig: {
    conversation: {
      backgroundSound: {
        sourceType: "preset",
        sourceId: "office2",
        volume: 0.15,
        crossfadeLoop: true,
      },
    },
  },
});

To disable, set source_type and source_id to null. Omitting background_sound on an update does not disable it.

Valid source_id values are office1, office2, restaurant, city, typing, and elevator1 through elevator4.

Voice filter reshapes the agent's generated voice. It does not equalize or denoise the background sound. The filter runs first; background sound is mixed under the filtered speech.

In the same Audio environment panel, set Voice filter to Off or a phone preset, then save.

• Built-in presets only. You cannot upload a custom file or point at an arbitrary URL.
• Audio environment controls are hidden when the agent is text-only.
• Background sound is not mixed into WhatsApp voice-message replies. WhatsApp calls still include it.
• Background sound cannot be set per conversation through client overrides; conversation_config_override does not include background_sound. You can still change it on a workflow node.

Play ambient audio only while a tool is running.

Choose a voice, speed, and other speech settings for the agent.