From 8d792de12b2e2f5685dd2e715f1da2999db211a7 Mon Sep 17 00:00:00 2001
From: Ramik Mukherjee <55507277+ramik10@users.noreply.github.com>
Date: Wed, 10 Jun 2026 00:49:44 +0530
Subject: [PATCH] Removed Emotion Detection section from how-vapi-works

Removed the section on Emotion Detection from the document as it's deprecated.
---
 fern/how-vapi-works.mdx | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/fern/how-vapi-works.mdx b/fern/how-vapi-works.mdx
index 91cf7fb4e..db3023e6e 100644
--- a/fern/how-vapi-works.mdx
+++ b/fern/how-vapi-works.mdx
@@ -62,12 +62,6 @@ They're not considered interruptions, they're just used to let the speaker know
 
 A backchannel cue used at the wrong moment can derail a user's statement. Vapi uses a proprietary fusion audio text model to determine the best moment to backchannel and to decide which backchannel cue is most appropriate to use.
 
-### Emotion Detection
-
-How a person says something is just as important as what they're saying. So we've trained a real-time audio model to extract the emotional inflection of the user's statement.
-
-This emotional information is then fed into the LLM, so knows to behave differently if the user is angry, annoyed, or confused.
-
 ### Filler Injection
 
 The output of LLMs tends to be formal, and not conversational. People speak with phrases like "umm", "ahh", "i mean", "like", "so", etc.