Advance Settings — Build a Lively Caller Experience
Written By Anand Raj
Last updated 24 days ago
Advance Settings is where you tune how your AI agent feels on a call — how creative it sounds, what background it picks up, how it fills silence while thinking, how it pronounces tricky words, and how long it stays on the line. Good defaults work for most businesses, but these knobs let you shape the caller experience for your industry.
Think of the AI agent like a human brain. It may take a beat to look things up. It can mishear unclear speech. Accents shift from one region to another — and just like a human, the agent won't catch everything. Advance Settings exist to cover the maximum of those gaps.
Note: If you are a direct business user and are not familiar with technical workflow configuration, do not make changes to the workflow. Contact your agency or raise a support ticket so the team can investigate and make the necessary changes.
Speech Settings
Speech Speed Sensitivity
Adjusts how quickly the assistant pauses when the caller interrupts. Lower it if the agent cuts the caller off, raise it if the agent waits too long before reacting.
Ambient Sound
Background sound played quietly under the call (e.g. Coffee Shop, office, café, or none). A small amount of ambient sound makes the call feel real and human instead of sterile. Use the volume slider to keep it subtle.
Thinking Sound
The AI sometimes needs a moment to read the right data from your systems. A Thinking Sound (e.g. Hold Music, soft tone, light typing) fills that gap so the caller doesn't hear dead silence and assume the line dropped.
Reminder Message, Pronunciation & Booster Keywords
Reminder Message Frequency
Controls how often the AI gently nudges the caller if they go quiet — set the Seconds to wait before reminding, and Times to limit how many reminders it sends before moving on.
Pronunciation
Every industry has words the model doesn't naturally pronounce well — brand names, medication names, locations, abbreviations. Click + Add and guide the model to say a specific word, name or phrase the right way.
Booster Keywords (Real-time Transcription)
Sometimes the AI mis-spells or mis-hears domain-specific words (your brand, product names, providers). Add them as Booster Keywords to expand the model's vocabulary so it picks up the right spelling on the call.
Call Settings
End Call Silence
If the caller stops speaking, this sets how long the agent waits before it ends the call automatically. Useful for catching dropped calls or callers who walked away, without holding the line forever.
Max Call Duration
Sets an upper cap on call length. Most calls resolve in 6–7 minutes — that's usually enough to answer a customer query or finish a workflow. If a call runs much longer, often the caller isn't sure what they need and the AI's quality starts to drop on very long conversations. A max duration also keeps your usage bill predictable.
Warm Transfer Summary
Choose whether the agent shares a short summary of the conversation with the receiving operator when it performs a warm transfer.
Share summary — the agent briefly recaps what happened on the call before connecting the operator, so the operator already knows why the caller is being transferred.
Skip summary — the transfer connects immediately with no recap. Only the summary is affected; the rest of the warm transfer actions, such as ringing the operator and connecting the caller, still happen normally. Use this if you prefer operators to greet callers fresh, or if your transfer destination already has context.
Frequently Asked Questions
My agent sounds too robotic — what should I change first?
My agent sounds too robotic — what should I change first?
Nudge Answer Creativity up by a small step, turn on Filler Phrases, and add a light Ambient Sound. Test a call after each change instead of moving everything at once.
Callers say there's awkward silence while the agent is "thinking" — fix?
Callers say there's awkward silence while the agent is "thinking" — fix?
Enable a Thinking Sound (e.g. Hold Music or a soft tone). It tells the caller the agent is still there and working.
The agent keeps mispronouncing our brand / product names. what to do here?
The agent keeps mispronouncing our brand / product names. what to do here?
Open your agent and go to Agent Identity & Conversation Flow → Advance Settings. Scroll to the Pronunciation section, click + Add, enter the word or phrase exactly as it's spelled, and provide a phonetic spelling that guides the model to say it correctly (e.g. "Kickcall" → "kik-kawl"). For words the agent also mis-transcribes in the live transcript, add them under Booster Keywords as well. Click Update to apply — changes take effect on new calls only.
What's a safe Max Call Duration?
What's a safe Max Call Duration?
For most businesses, somewhere around 10–15 minutes is plenty — well above the typical 6–7 minute resolution time, with headroom for edge cases. Going much longer rarely improves outcomes and increases cost.
Can the operator hear a summary before the warm transfer connects?
Can the operator hear a summary before the warm transfer connects?
Yes. In Advance Settings, set Warm Transfer Summary to Share summary. The agent will give the receiving operator a brief recap before connecting them.
Select Skip summary if you prefer the operator to answer without a recap - this only removes the spoken summary; the transfer itself still rings the operator and connects the caller as usual.
Will these settings affect existing calls?
Will these settings affect existing calls?
No. Advance Settings apply to new calls only after you click Update.
More in Identity & Conversation Flow:
Was this helpful?
Still need help? Ask the team