Configure voice, speech recognition and turn-taking

Intermediate⏱ 15 min
🔒Join free to watch this video lessonFree account · takes 30 seconds · no card neededJoin free & watchAlready a member? Log in
The 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

🔓 Unlock the full lesson — free

Create a free account to read the step-by-step guide, see the worked example, take the quiz, download templates and track your progress.

💬 Questions about this lesson?
Ask the community — practitioners and the BFOUNT team answer.
Ask a question
Was this lesson helpful?