Configure voice, speech recognition and turn-taking
🔒Join free to watch this video lessonFree account · takes 30 seconds · no card neededJoin free & watchAlready a member? Log inThe settings that make an agent feel natural: voice choice, speed, endpointing, interruptions, filler words and silence handling.
In this lesson you’ll learn to
- I changed one setting at a time
- I added custom keywords
- I set max call duration and silence timeout
Outcome of this lesson
You can configure a platform so the agent sounds natural on real calls.
Step 1 — Choose a voice
• Pick a voice that fits the brand: calm and warm for healthcare, upbeat for retail.
• Choose voices designed for conversational use; listen to a 30-second sample, not just a one-line preview.
• Only use voices you have the rights to. Cloning a real person’s voice requires their consent.
• Match language and accent to your callers.
Step 2 — Set pace
Start at normal speed, test slightly slower for older callers or complex information. Fast, flat delivery feels robotic.
Step 3 — Speech recognition
• Select the right language and region model.
• Add custom vocabulary / keywords for brand names, product names, local street names and medical or technica
💬 Questions about this lesson?
Ask a questionAsk the community — practitioners and the BFOUNT team answer.
Was this lesson helpful?