test cleanup

src/pipecat/frames/frames.py

@@ -307,7 +307,7 @@ class UserStoppedSpeakingFrame(ControlFrame):
 @dataclass
 class TTSStartedFrame(ControlFrame):
     """Used to indicate the beginning of a TTS response. Following
-    AudioRawFrames are part of the TTS response until an TTSEndFrame. These
+    AudioRawFrames are part of the TTS response until an TTSStoppedFrame. These
     frames can be used for aggregating audio frames in a transport to optimize
     the size of frames sent to the session, without needing to control this in
     the TTS service.

src/pipecat/pipeline/merge_pipeline.py

@@ -1,5 +1,5 @@
 from typing import List
-from pipecat.frames.frames import EndFrame, EndPipeFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 
 
@@ -16,8 +16,7 @@ class SequentialMergePipeline(Pipeline):
             while True:
                 frame = await pipeline.sink.get()
                 if isinstance(
-                        frame, EndFrame) or isinstance(
+                        frame, EndFrame):
-                        frame, EndPipeFrame):
                     break
                 await self.sink.put(frame)
 

src/pipecat/serializers/protobuf_serializer.py

@@ -1,6 +1,6 @@
 import dataclasses
 from typing import Text
-from pipecat.frames.frames import AudioFrame, Frame, TextFrame, TranscriptionFrame
+from pipecat.frames.frames import AudioRawFrame, Frame, TextFrame, TranscriptionFrame
 import pipecat.frames.protobufs.frames_pb2 as frame_protos
 from pipecat.serializers.abstract_frame_serializer import FrameSerializer
 
@@ -8,7 +8,7 @@ from pipecat.serializers.abstract_frame_serializer import FrameSerializer
 class ProtobufFrameSerializer(FrameSerializer):
     SERIALIZABLE_TYPES = {
         TextFrame: "text",
-        AudioFrame: "audio",
+        AudioRawFrame: "audio",
         TranscriptionFrame: "transcription"
     }
 

src/pipecat/transports/services/daily.py

@@ -17,8 +17,8 @@ from functools import partial
 from typing import Any, Callable, Mapping
 
 from daily import (
-    CallClient,
     Daily,
+    CallClient,
     EventHandler,
     VirtualCameraDevice,
     VirtualMicrophoneDevice,

tests/test_aggregators.py

@@ -9,9 +9,9 @@ from pipecat.processors.aggregators.gated import GatedAggregator
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
 
 from pipecat.frames.frames import (
-    AudioFrame,
+    AudioRawFrame,
     EndFrame,
-    ImageFrame,
+    ImageRawFrame,
     LLMResponseEndFrame,
     LLMResponseStartFrame,
     Frame,
@@ -45,26 +45,26 @@ class TestDailyFrameAggregators(unittest.IsolatedAsyncioTestCase):
     async def test_gated_accumulator(self):
         gated_aggregator = GatedAggregator(
             gate_open_fn=lambda frame: isinstance(
-                frame, ImageFrame), gate_close_fn=lambda frame: isinstance(
+                frame, ImageRawFrame), gate_close_fn=lambda frame: isinstance(
                 frame, LLMResponseStartFrame), start_open=False, )
 
         frames = [
             LLMResponseStartFrame(),
             TextFrame("Hello, "),
             TextFrame("world."),
-            AudioFrame(b"hello"),
+            AudioRawFrame(b"hello", 1, 1),
-            ImageFrame(b"image", (0, 0)),
+            ImageRawFrame(b"image", (0, 0)),
-            AudioFrame(b"world"),
+            AudioRawFrame(b"world", 1, 1),
             LLMResponseEndFrame(),
         ]
 
         expected_output_frames = [
-            ImageFrame(b"image", (0, 0)),
+            ImageRawFrame(b"image", (0, 0)),
             LLMResponseStartFrame(),
             TextFrame("Hello, "),
             TextFrame("world."),
-            AudioFrame(b"hello"),
+            AudioRawFrame(b"hello", 1, 1),
-            AudioFrame(b"world"),
+            AudioRawFrame(b"world", 1, 1),
             LLMResponseEndFrame(),
         ]
         for frame in frames:

tests/to_be_updated/test_websocket_transport.py

@@ -2,7 +2,7 @@ import asyncio
 import unittest
 from unittest.mock import AsyncMock, patch, Mock
 
-from pipecat.frames.frames import AudioFrame, EndFrame, TextFrame, TTSEndFrame, TTSStartFrame
+from pipecat.frames.frames import AudioRawFrame, EndFrame, TextFrame, TTSStoppedFrame, TTSStartedFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.transports.websocket_transport import WebSocketFrameProcessor, WebsocketTransport
 
@@ -52,10 +52,10 @@ class TestWebSocketTransportService(unittest.IsolatedAsyncioTestCase):
         processor = WebSocketFrameProcessor(audio_frame_size=4)
 
         source_frames = [
-            TTSStartFrame(),
+            TTSStartedFrame(),
-            AudioFrame(b"1234"),
+            AudioRawFrame(b"1234", 1, 1),
-            AudioFrame(b"5678"),
+            AudioRawFrame(b"5678", 1, 1),
-            TTSEndFrame(),
+            TTSStoppedFrame(),
             TextFrame("hello world")
         ]
 
@@ -65,9 +65,9 @@ class TestWebSocketTransportService(unittest.IsolatedAsyncioTestCase):
                 frames.append(output_frame)
 
         self.assertEqual(len(frames), 3)
-        self.assertIsInstance(frames[0], AudioFrame)
+        self.assertIsInstance(frames[0], AudioRawFrame)
         self.assertEqual(frames[0].data, b"1234")
-        self.assertIsInstance(frames[1], AudioFrame)
+        self.assertIsInstance(frames[1], AudioRawFrame)
         self.assertEqual(frames[1].data, b"5678")
         self.assertIsInstance(frames[2], TextFrame)
         self.assertEqual(frames[2].text, "hello world")