Skip to main content
The Settings tab groups call behavior first, then analysis, webhooks, and saved artifacts. The call behavior cards appear in this order: Noise Handling, Background Sound, Voicemail, Duration Limit, and Silence Handling.
If you used Vocily before: the Outcome tab has been folded into this one. Custom Analysis, Webhooks, and Saved Artifacts are near the end of this page. Interruption Sensitivity and Response Eagerness moved out, to the Transcriber pill.Transfer Call and End Call are configured on Tools.

Noise Handling

Choose Off, Standard, High Noise, or Strict Guard for progressively stricter background-noise handling. These four buttons are the complete control. New agents start on Standard. Start with the default and change one control at a time. A noisy line may need stronger noise handling.

Background Sound

Adds a soft sound behind the agent on phone calls, like an office or a café. Every agent starts with No sound. Manage sounds opens the workspace sound library.
Phone calls only. It plays on inbound, outbound, API and campaign calls, and in the dashboard’s Call test. It does not play in the Talk test or the website widget.
This is different from Noise Handling, which filters the noise around the caller. Background Sound adds sound on the agent’s side.
  • Sound: No sound, a built-in sound, or one your workspace uploaded. Use the + button next to it to upload a new one.
  • Background volume: 0 to 100%, default 15%. With a built-in sound, the agent’s voice stays louder even at 100%. Your own sounds play at their recorded level, scaled by this slider.
  • With greeting: plays the agent’s greeting over the sound.
  • Sound only: plays just the sound at the volume you set.

Built-in sounds

Sounds with voices can make the agent pause. Café, Call centre, Busy office, Office with typing, Street market and Restaurant have people talking in them. On speakerphone, that can leak into the caller’s microphone. Keep the volume low, or use Quiet office, Home, City traffic or Soft line static.

Your own sounds

Upload a recording with the + button next to the sound picker, or in Settings → Sounds. Every agent in the workspace can use an uploaded sound. People who can manage knowledge bases can also upload, rename and delete sounds. See Roles and permissions. Vocily converts the file to phone quality but does not edit it. Upload a steady recording that loops well, and use the volume slider to set the level. Uploaded sounds can only be chosen in the dashboard. The API and Lily can set the built-in sounds.

Deleting a sound

Before you delete a sound, the dashboard lists every agent using it, live or draft, and asks you to type delete. Those agents then play no background sound, so pick another sound for them first.

During a call

Like everything on this tab, changes reach callers once the version is published and made live.
Lily can list the built-in sounds, set one and change the volume. Ask her, then accept or reject what she stages.

Voicemail

On outbound calls, the agent listens to what the other side says in the first seconds and tells a voicemail greeting apart from a person. That covers carrier voicemail and phone voicemail such as iPhone’s, in English, Hindi and Arabic. When it is not sure, it treats the call as a person. Choose what the agent does when it hears voicemail: Voicemail message is said word for word, up to 500 characters. You can use variables like {{name}}, the same way as in the greeting. When there is no beep, the agent speaks after about two seconds of quiet, and never later than 30 seconds after it heard voicemail. If a person starts talking while the message plays, the agent stops and talks to them. When a carrier message answers instead, such as “the number you are calling is switched off”, the call is marked No answer and no message is left. With Hang up or Leave a message, the agent hangs up straight away. The greeting still plays the moment the call is answered, and inbound calls are never affected. A campaign uses the agent version that was live when the campaign was created, so publish this setting before you create the campaign.

Duration Limit

Maximum duration is the safety ceiling for a live call. It accepts 1 to 30 minutes and defaults to 10. The runtime tries to wrap up shortly before the limit so the call does not end in the middle of an answer. Closing message is what the caller hears when the limit is reached. The limit also protects against runaway provider and model costs; it is not a replacement for a clear call flow.

Silence Handling

Silence reminder is on by default. Remind after accepts 3 seconds up to one second less than the end timer, and defaults to 25. Its Reminder message is a brief check-in. End after silence ends the call when neither side has spoken for the configured period. It accepts 5 to 120 seconds and defaults to 45. The second Closing message is played before that call ends. Both timers measure the same quiet period; the reminder does not restart the end timer. Silence handling is useful for abandoned calls and dropped audio, but a very short timeout can cut off callers who think before answering.

Custom Analysis

Custom Analysis turns each finished conversation into structured data you define - a summary, a classification, a number, a list. The values are defined as groups in the workspace library; this card chooses which groups this agent runs.
  • Attach a group from the workspace library when one is available.
  • Select Detach on an attached group to remove it from this agent.
  • Manage groups opens the workspace library, where the definitions live.
  • The toggle stops all extraction for this agent without changing what is attached.
Detaching a group here never deletes it - the definition stays in the library for other agents. Every new agent starts with Default Analysis already attached, which gives you a call summary, caller sentiment, outcome, and language on every conversation without any setup.

Custom Analysis: full reference

Groups and analyses, editing Default Analysis, result formats, run conditions, regex extraction, testing, limits, and how results reach your webhooks.

Webhooks

Add an HTTPS endpoint to receive this agent’s call events as they happen. Use a webhook to send event data to your system after a call.

Webhooks reference

Event types, payload shapes, retries, and signature verification.

Saved Artifacts

Choose what Vocily retains after each finished conversation. Both are on by default for new agents.
  • Save call audio - keep a playable recording in Conversation History for review, coaching, and call-quality investigation.
  • Save transcript - keep the conversation transcript available for review, analysis, and follow-up.
Choose the settings that fit your team’s review and privacy needs.

Save and test

Select Save Changes after editing. Everything on this tab belongs to the version you are editing - save the draft, then publish and make it live when you are ready. Test at least these paths before going live:
  1. Interrupt the agent while it is speaking.
  2. Stay silent long enough to hear the reminder and the timeout behavior.
  3. Let a call run to the duration limit and check the wrap-up.
  4. Confirm the analysis values you expect appear on the conversation afterwards.
  5. If you chose a background sound, listen to it on a real phone call, not only in Preview.

What’s next

  • Turn transfer, hold, and closing behavior on in Tools.
  • Choose which number or channel reaches the agent in Deploy.
  • Review what came out in Conversation History.