diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0c5c30b0e..024bd10f0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -86,6 +86,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   removed in a future version. Use the `/start` endpoint in its place. In the
   meantime, both endpoints work and deliver equivalent functionality.
 
+- Added `processor` field to `ErrorFrame` to indicate `FrameProcessor` that generated the error.
+
 ## [0.0.77] - 2025-07-31
 
 ### Added
diff --git a/src/pipecat/frames/frames.py b/src/pipecat/frames/frames.py
index 94e799aa6..94a60787d 100644
--- a/src/pipecat/frames/frames.py
+++ b/src/pipecat/frames/frames.py
@@ -664,10 +664,12 @@ class ErrorFrame(SystemFrame):
     Parameters:
         error: Description of the error that occurred.
         fatal: Whether the error is fatal and requires bot shutdown.
+        source: The frame processor that generated the error.
     """
 
     error: str
     fatal: bool = False
+    processor: Optional["FrameProcessor"] = None
 
     def __str__(self):
         return f"{self.name}(error: {self.error}, fatal: {self.fatal})"
diff --git a/src/pipecat/processors/frame_processor.py b/src/pipecat/processors/frame_processor.py
index a049fabdb..e6611a161 100644
--- a/src/pipecat/processors/frame_processor.py
+++ b/src/pipecat/processors/frame_processor.py
@@ -494,6 +494,8 @@ class FrameProcessor(BaseObject):
         Args:
             error: The error frame to push.
         """
+        if not error.processor:
+            error.processor = self
         await self.push_frame(error, FrameDirection.UPSTREAM)
 
     async def push_frame(self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM):
diff --git a/src/pipecat/services/anthropic/llm.py b/src/pipecat/services/anthropic/llm.py
index d7c703ebb..15c4cebee 100644
--- a/src/pipecat/services/anthropic/llm.py
+++ b/src/pipecat/services/anthropic/llm.py
@@ -26,6 +26,7 @@ from pydantic import BaseModel, Field
 
 from pipecat.adapters.services.anthropic_adapter import AnthropicLLMAdapter
 from pipecat.frames.frames import (
+    ErrorFrame,
     Frame,
     FunctionCallCancelFrame,
     FunctionCallInProgressFrame,
@@ -346,6 +347,7 @@ class AnthropicLLMService(LLMService):
             await self._call_event_handler("on_completion_timeout")
         except Exception as e:
             logger.exception(f"{self} exception: {e}")
+            await self.push_error(ErrorFrame(f"{e}"))
         finally:
             await self.stop_processing_metrics()
             await self.push_frame(LLMFullResponseEndFrame())
diff --git a/src/pipecat/services/deepgram/stt.py b/src/pipecat/services/deepgram/stt.py
index 56658cad5..8381135d9 100644
--- a/src/pipecat/services/deepgram/stt.py
+++ b/src/pipecat/services/deepgram/stt.py
@@ -13,6 +13,7 @@ from loguru import logger
 from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
+    ErrorFrame,
     Frame,
     InterimTranscriptionFrame,
     StartFrame,
@@ -246,6 +247,7 @@ class DeepgramSTTService(STTService):
     async def _on_error(self, *args, **kwargs):
         error: ErrorResponse = kwargs["error"]
         logger.warning(f"{self} connection error, will retry: {error}")
+        await self.push_error(ErrorFrame(f"{error}"))
         await self.stop_all_metrics()
         # NOTE(aleix): we don't disconnect (i.e. call finish on the connection)
         # because this triggers more errors internally in the Deepgram SDK. So,