diff --git a/fern/apis/api/openapi.json b/fern/apis/api/openapi.json
index 430e2da9..f1b22d83 100644
--- a/fern/apis/api/openapi.json
+++ b/fern/apis/api/openapi.json
@@ -7518,14 +7518,19 @@
             ]
           },
           "model": {
-            "type": "string",
             "description": "This is the model that will be used for the transcription.",
-            "enum": [
-              "scribe_v1"
+            "oneOf": [
+              {
+                "enum": [
+                  "scribe_v1",
+                  "scribe_v2_realtime"
+                ]
+              }
             ]
           },
           "language": {
             "type": "string",
+            "description": "This is the language that will be used for the transcription.",
             "enum": [
               "aa",
               "ab",
@@ -7714,6 +7719,34 @@
               "zu"
             ]
           },
+          "silenceThresholdSeconds": {
+            "type": "number",
+            "description": "This is the number of seconds of silence before VAD commits (0.3-3.0).",
+            "minimum": 0.3,
+            "maximum": 3,
+            "example": 1.5
+          },
+          "confidenceThreshold": {
+            "type": "number",
+            "description": "This is the VAD sensitivity (0.1-0.9, lower indicates more sensitive).",
+            "minimum": 0.1,
+            "maximum": 0.9,
+            "example": 0.4
+          },
+          "minSpeechDurationMs": {
+            "type": "number",
+            "description": "This is the minimum speech duration for VAD (50-2000ms).",
+            "minimum": 50,
+            "maximum": 2000,
+            "example": 100
+          },
+          "minSilenceDurationMs": {
+            "type": "number",
+            "description": "This is the minimum silence duration for VAD (50-2000ms).",
+            "minimum": 50,
+            "maximum": 2000,
+            "example": 100
+          },
           "fallbackPlan": {
             "description": "This is the plan for voice provider fallbacks in the event that the primary voice provider fails.",
             "allOf": [
@@ -9343,14 +9376,19 @@
             ]
           },
           "model": {
-            "type": "string",
             "description": "This is the model that will be used for the transcription.",
-            "enum": [
-              "scribe_v1"
+            "oneOf": [
+              {
+                "enum": [
+                  "scribe_v1",
+                  "scribe_v2_realtime"
+                ]
+              }
             ]
           },
           "language": {
             "type": "string",
+            "description": "This is the language that will be used for the transcription.",
             "enum": [
               "aa",
               "ab",
@@ -9538,6 +9576,34 @@
               "zh",
               "zu"
             ]
+          },
+          "silenceThresholdSeconds": {
+            "type": "number",
+            "description": "This is the number of seconds of silence before VAD commits (0.3-3.0).",
+            "minimum": 0.3,
+            "maximum": 3,
+            "example": 1.5
+          },
+          "confidenceThreshold": {
+            "type": "number",
+            "description": "This is the VAD sensitivity (0.1-0.9, lower indicates more sensitive).",
+            "minimum": 0.1,
+            "maximum": 0.9,
+            "example": 0.4
+          },
+          "minSpeechDurationMs": {
+            "type": "number",
+            "description": "This is the minimum speech duration for VAD (50-2000ms).",
+            "minimum": 50,
+            "maximum": 2000,
+            "example": 100
+          },
+          "minSilenceDurationMs": {
+            "type": "number",
+            "description": "This is the minimum silence duration for VAD (50-2000ms).",
+            "minimum": 50,
+            "maximum": 2000,
+            "example": 100
           }
         },
         "required": [