From 2910b683a477a1011b7c0cd2bd56548bf43eaa2a Mon Sep 17 00:00:00 2001
From: Mark Backman <mark@daily.co>
Date: Mon, 22 Dec 2025 12:54:06 -0500
Subject: [PATCH] Fix STT services that rely on VAD stop speaking status to
 finalize the transcript (#3283)

Updates to AssemblyAISTTService, CartesiaSTTService, DeepgramSageMakerSTTService, DeepgramSTTService to use VADUser*SpeakingFrame
---
 src/pipecat/services/assemblyai/stt.py         |  8 ++++----
 src/pipecat/services/cartesia/stt.py           |  8 ++++----
 src/pipecat/services/deepgram/stt.py           | 10 ++++------
 src/pipecat/services/deepgram/stt_sagemaker.py |  8 ++++----
 4 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/src/pipecat/services/assemblyai/stt.py b/src/pipecat/services/assemblyai/stt.py
index 142125f29..4d7f91cc2 100644
--- a/src/pipecat/services/assemblyai/stt.py
+++ b/src/pipecat/services/assemblyai/stt.py
@@ -25,8 +25,8 @@ from pipecat.frames.frames import (
     InterimTranscriptionFrame,
     StartFrame,
     TranscriptionFrame,
-    UserStartedSpeakingFrame,
-    UserStoppedSpeakingFrame,
+    VADUserStartedSpeakingFrame,
+    VADUserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.stt_service import WebsocketSTTService
@@ -160,9 +160,9 @@ class AssemblyAISTTService(WebsocketSTTService):
             direction: Direction of frame processing.
         """
         await super().process_frame(frame, direction)
-        if isinstance(frame, UserStartedSpeakingFrame):
+        if isinstance(frame, VADUserStartedSpeakingFrame):
             await self.start_ttfb_metrics()
-        elif isinstance(frame, UserStoppedSpeakingFrame):
+        elif isinstance(frame, VADUserStoppedSpeakingFrame):
             if (
                 self._vad_force_turn_endpoint
                 and self._websocket
diff --git a/src/pipecat/services/cartesia/stt.py b/src/pipecat/services/cartesia/stt.py
index 3099708e4..6c4a2640e 100644
--- a/src/pipecat/services/cartesia/stt.py
+++ b/src/pipecat/services/cartesia/stt.py
@@ -23,8 +23,8 @@ from pipecat.frames.frames import (
     InterimTranscriptionFrame,
     StartFrame,
     TranscriptionFrame,
-    UserStartedSpeakingFrame,
-    UserStoppedSpeakingFrame,
+    VADUserStartedSpeakingFrame,
+    VADUserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.stt_service import WebsocketSTTService
@@ -221,9 +221,9 @@ class CartesiaSTTService(WebsocketSTTService):
         """
         await super().process_frame(frame, direction)
 
-        if isinstance(frame, UserStartedSpeakingFrame):
+        if isinstance(frame, VADUserStartedSpeakingFrame):
             await self.start_metrics()
-        elif isinstance(frame, UserStoppedSpeakingFrame):
+        elif isinstance(frame, VADUserStoppedSpeakingFrame):
             # Send finalize command to flush the transcription session
             if self._websocket and self._websocket.state is State.OPEN:
                 await self._websocket.send("finalize")
diff --git a/src/pipecat/services/deepgram/stt.py b/src/pipecat/services/deepgram/stt.py
index 11be561b1..63c89f880 100644
--- a/src/pipecat/services/deepgram/stt.py
+++ b/src/pipecat/services/deepgram/stt.py
@@ -6,7 +6,6 @@
 
 """Deepgram speech-to-text service implementation."""
 
-import asyncio
 from typing import AsyncGenerator, Dict, Optional
 
 from loguru import logger
@@ -14,13 +13,12 @@ from loguru import logger
 from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
-    ErrorFrame,
     Frame,
     InterimTranscriptionFrame,
     StartFrame,
     TranscriptionFrame,
-    UserStartedSpeakingFrame,
-    UserStoppedSpeakingFrame,
+    VADUserStartedSpeakingFrame,
+    VADUserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.stt_service import STTService
@@ -329,10 +327,10 @@ class DeepgramSTTService(STTService):
         """
         await super().process_frame(frame, direction)
 
-        if isinstance(frame, UserStartedSpeakingFrame) and not self.vad_enabled:
+        if isinstance(frame, VADUserStartedSpeakingFrame) and not self.vad_enabled:
             # Start metrics if Deepgram VAD is disabled & pipeline VAD has detected speech
             await self.start_metrics()
-        elif isinstance(frame, UserStoppedSpeakingFrame):
+        elif isinstance(frame, VADUserStoppedSpeakingFrame):
             # https://developers.deepgram.com/docs/finalize
             await self._connection.finalize()
             logger.trace(f"Triggered finalize event on: {frame.name=}, {direction=}")
diff --git a/src/pipecat/services/deepgram/stt_sagemaker.py b/src/pipecat/services/deepgram/stt_sagemaker.py
index cc765f83a..0910bd760 100644
--- a/src/pipecat/services/deepgram/stt_sagemaker.py
+++ b/src/pipecat/services/deepgram/stt_sagemaker.py
@@ -26,8 +26,8 @@ from pipecat.frames.frames import (
     InterimTranscriptionFrame,
     StartFrame,
     TranscriptionFrame,
-    UserStartedSpeakingFrame,
-    UserStoppedSpeakingFrame,
+    VADUserStartedSpeakingFrame,
+    VADUserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.aws.sagemaker.bidi_client import SageMakerBidiClient
@@ -432,9 +432,9 @@ class DeepgramSageMakerSTTService(STTService):
         await super().process_frame(frame, direction)
 
         # Start metrics when user starts speaking (if VAD is not provided by Deepgram)
-        if isinstance(frame, UserStartedSpeakingFrame):
+        if isinstance(frame, VADUserStartedSpeakingFrame):
             await self.start_metrics()
-        elif isinstance(frame, UserStoppedSpeakingFrame):
+        elif isinstance(frame, VADUserStoppedSpeakingFrame):
             # Send finalize message to Deepgram when user stops speaking
             # This tells Deepgram to flush any remaining audio and return final results
             if self._client and self._client.is_active: