From 714c11289a56e9df3d9a169a8ac879f917e4ddba Mon Sep 17 00:00:00 2001
From: Dhruva Reddy <dhruva@vapi.ai>
Date: Mon, 16 Mar 2026 16:22:02 -0700
Subject: [PATCH] docs: add transcriptType and turnId fields to WebSocket
 message docs

Document three new optional fields from VapiAI/vapi#10548:
- transcriptType (partial|final) on transcriber-response messages
- turnId on model-output and user-interrupted messages

Made-with: Cursor
---
 fern/customization/custom-transcriber.mdx | 20 ++++++++++++++++----
 fern/server-url/events.mdx                | 10 +++++++---
 2 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/fern/customization/custom-transcriber.mdx b/fern/customization/custom-transcriber.mdx
index 771b4dfc7..bd6aeb24d 100644
--- a/fern/customization/custom-transcriber.mdx
+++ b/fern/customization/custom-transcriber.mdx
@@ -43,14 +43,22 @@ You'll learn how to:
     Your server forwards the audio to Deepgram (or your chosen transcriber) using its SDK. Deepgram processes the audio and returns transcript events that include a `channel_index` (e.g. `[0, ...]` for customer, `[1, ...]` for assistant). The service buffers the incoming data, processes the transcript events (with debouncing and channel detection), and emits a final transcript.
   </Step>
   <Step title="Response">
-    The final transcript is sent back to Vapi as a JSON message:
+    The transcript is sent back to Vapi as a JSON message:
     ```json
     {
       "type": "transcriber-response",
       "transcription": "The transcribed text",
-      "channel": "customer" // or "assistant"
+      "channel": "customer",
+      "transcriptType": "final"
     }
     ```
+
+    The optional `transcriptType` field controls how Vapi handles the transcript:
+
+    - **`"final"`** (default) — the transcription is definitive.
+    - **`"partial"`** — the transcription is provisional and may be superseded by a later message. Each partial replaces the previous one until a `"final"` arrives.
+
+    If omitted, `transcriptType` defaults to `"final"` for backward compatibility.
   </Step>
 </Steps>
 
@@ -362,6 +370,7 @@ You'll learn how to:
             type: "transcriber-response",
             transcription: text,
             channel,
+            transcriptType: "final",
           };
           ws.send(JSON.stringify(response));
           logger.logDetailed("INFO", "Sent transcription to client", "Server", {
@@ -423,12 +432,13 @@ You'll learn how to:
     - The `"start"` message initializes the Deepgram session.
     - PCM audio data is forwarded to Deepgram.
     - Deepgram returns transcript events, which are processed with channel detection and debouncing.
-    - The final transcript is sent back as a JSON message:
+    - The transcript is sent back as a JSON message:
       ```json
       {
         "type": "transcriber-response",
         "transcription": "The transcribed text",
-        "channel": "customer" // or "assistant"
+        "channel": "customer",
+        "transcriptType": "final"
       }
       ```
   </Step>
@@ -444,6 +454,8 @@ You'll learn how to:
   The solution buffers PCM audio and performs simple validation (e.g. ensuring stereo PCM data length is a multiple of 4). If the audio data is malformed, it is trimmed to a valid length.
 - **Channel detection:**  
   Transcript events from Deepgram include a `channel_index` array. The service uses the first element to determine whether the transcript is from the customer (`0`) or the assistant (`1`). Ensure Deepgram's response format remains consistent with this logic.
+- **Partial transcripts:**  
+  Set `transcriptType` to `"partial"` to send progressive transcription updates. Each partial supersedes the previous one until a `"final"` message arrives. This is useful for STT providers that emit fast, low-latency partials that get refined over time (e.g. ElevenLabs Scribe). If `transcriptType` is omitted, Vapi treats the message as `"final"`.
 
 ---
 
diff --git a/fern/server-url/events.mdx b/fern/server-url/events.mdx
index 0a33f737b..f6a9178b3 100644
--- a/fern/server-url/events.mdx
+++ b/fern/server-url/events.mdx
@@ -289,13 +289,14 @@ For final-only events, you may receive `type: "transcript[transcriptType=\"final
 
 ### Model Output
 
-Tokens or tool-call outputs as the model generates.
+Tokens or tool-call outputs as the model generates. The optional `turnId` groups all tokens from the same LLM response, so you can correlate output with a specific turn.
 
 ```json
 {
   "message": {
     "type": "model-output",
-    "output": { /* token or tool call */ }
+    "output": { /* token or tool call */ },
+    "turnId": "abc-123"
   }
 }
 ```
@@ -339,10 +340,13 @@ Fires whenever a transfer occurs.
 
 ### User Interrupted
 
+Sent when the user interrupts the assistant. The optional `turnId` identifies the LLM turn that was interrupted, matching the `turnId` on `model-output` messages so you can discard that turn's tokens.
+
 ```json
 {
   "message": {
-    "type": "user-interrupted"
+    "type": "user-interrupted",
+    "turnId": "abc-123"
   }
 }
 ```