How to fix Interruption/Barge-In ✅

Hey guys, been able to smooth out the barge in and interruption capabilities, for a lot of my clients voice agents:

Here’s how:

(1) shorter, smarter TTS chunks and strict stop-speaking rules, and

(2) smaller, better RAG chunks so the LLM answers in shorter bursts.

Do both.

KB via Trieve (BYOD), set chunk size ~200–600 tokens with 15–20% overlap, and prefer heading-based or GPT-4o optimized chunking for coherence.

This yields tighter citations and shorter LLM replies (less rambling = easier interruption).

Hope this helps you guys🚀

2 comments

skool.com/assistable

We give you the most dominantly unfair advantage in the agency space. The most installed GoHighLevel AI ever.

Leaderboard (30-day)

+13

+11

+11