chore: fix deepgram

Author: margaritagomez

fern/customization/voice-pipeline-configuration.mdx

@@ -205,7 +205,7 @@ Uses AI models to analyze speech patterns, context, and audio cues to predict wh
 
 ### Deepgram Flux configuration
 
-Deepgram Flux's end-of-turn detection is configured at the transcriber level, allowing you to fine-tune how aggressive or conservative the bot should be in detecting when users finish speaking.
+Deepgram Flux's end-of-turn detection is configured at the transcriber level, allowing you to fine-tune how aggressive or conservative the bot should be in detecting when users finish speaking. Do NOT set a `smartEndpointingPlan` to leverage Deepgram's end-of-turn events.
 
 **Configuration parameters:**
 
@@ -224,7 +224,8 @@ Deepgram Flux's end-of-turn detection is configured at the transcriber level, al
 ```json
 {
   "transcriber": {
-    "provider": "flux-general-en",
+    "provider": "deepgram",
+    "model": "flux-general-en",
     "language": "en",
     "eotThreshold": 0.7,
     "eotTimeoutMs": 5000
@@ -669,15 +670,16 @@ User Interrupts → Assistant Audio Stopped → backoffSeconds Blocks All Output
 ```json
 {
   "transcriber": {
-    "provider": "flux-general-en",
+    "provider": "deepgram",
+    "model": "flux-general-en",
     "language": "en",
     "eotThreshold": 0.7,
-    "eotTimeoutMs": 5000,
+    "eotTimeoutMs": 5000
   },
   "stopSpeakingPlan": {
     "numWords": 2,
     "voiceSeconds": 0.2,
-    "backoffSeconds": 1.0
+    "backoffSeconds": 1.0,
     "acknowledgementPhrases": [
       "okay",
       "right",