Merge pull request #480 from pipecat-ai/aleix/input-output-frames

introduce input/output audio and image frames

examples/foundational/05a-local-sync-speech-and-image.py

@@ -11,7 +11,13 @@ import sys
 
 import tkinter as tk
 
-from pipecat.frames.frames import AudioRawFrame, Frame, URLImageRawFrame, LLMMessagesFrame, TextFrame
+from pipecat.frames.frames import (
+    Frame,
+    OutputAudioRawFrame,
+    TTSAudioRawFrame,
+    URLImageRawFrame,
+    LLMMessagesFrame,
+    TextFrame)
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
@@ -65,9 +71,9 @@ async def main():
                 async def process_frame(self, frame: Frame, direction: FrameDirection):
                     await super().process_frame(frame, direction)
 
-                    if isinstance(frame, AudioRawFrame):
+                    if isinstance(frame, TTSAudioRawFrame):
                         self.audio.extend(frame.audio)
-                        self.frame = AudioRawFrame(
+                        self.frame = OutputAudioRawFrame(
                             bytes(self.audio), frame.sample_rate, frame.num_channels)
 
             class ImageGrabber(FrameProcessor):

examples/foundational/06a-image-sync.py

@@ -11,7 +11,7 @@ import sys
 
 from PIL import Image
 
-from pipecat.frames.frames import ImageRawFrame, Frame, SystemFrame, TextFrame
+from pipecat.frames.frames import Frame, OutputImageRawFrame, SystemFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -52,9 +52,16 @@ class ImageSyncAggregator(FrameProcessor):
         await super().process_frame(frame, direction)
 
         if not isinstance(frame, SystemFrame) and direction == FrameDirection.DOWNSTREAM:
-            await self.push_frame(ImageRawFrame(image=self._speaking_image_bytes, size=(1024, 1024), format=self._speaking_image_format))
+            await self.push_frame(OutputImageRawFrame(
+                image=self._speaking_image_bytes,
+                size=(1024, 1024),
+                format=self._speaking_image_format)
+            )
             await self.push_frame(frame)
-            await self.push_frame(ImageRawFrame(image=self._waiting_image_bytes, size=(1024, 1024), format=self._waiting_image_format))
+            await self.push_frame(OutputImageRawFrame(
+                image=self._waiting_image_bytes,
+                size=(1024, 1024),
+                format=self._waiting_image_format))
         else:
             await self.push_frame(frame)
 

examples/foundational/09-mirror.py

@@ -8,9 +8,11 @@ import aiohttp
 import asyncio
 import sys
 
+from pipecat.frames.frames import Frame, InputAudioRawFrame, InputImageRawFrame, OutputAudioRawFrame, OutputImageRawFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.transports.services.daily import DailyTransport, DailyParams
 
 from runner import configure
@@ -24,6 +26,27 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
 
+class MirrorProcessor(FrameProcessor):
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, InputAudioRawFrame):
+            await self.push_frame(OutputAudioRawFrame(
+                audio=frame.audio,
+                sample_rate=frame.sample_rate,
+                num_channels=frame.num_channels)
+            )
+        elif isinstance(frame, InputImageRawFrame):
+            await self.push_frame(OutputImageRawFrame(
+                image=frame.image,
+                size=frame.size,
+                format=frame.format)
+            )
+        else:
+            await self.push_frame(frame, direction)
+
+
 async def main():
     async with aiohttp.ClientSession() as session:
         (room_url, token) = await configure(session)
@@ -44,7 +67,7 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             transport.capture_participant_video(participant["id"])
 
-        pipeline = Pipeline([transport.input(), transport.output()])
+        pipeline = Pipeline([transport.input(), MirrorProcessor(), transport.output()])
 
         runner = PipelineRunner()
 

examples/foundational/09a-local-mirror.py

@@ -10,9 +10,11 @@ import sys
 
 import tkinter as tk
 
+from pipecat.frames.frames import Frame, InputAudioRawFrame, InputImageRawFrame, OutputAudioRawFrame, OutputImageRawFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.tk import TkLocalTransport
 from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -27,6 +29,25 @@ load_dotenv(override=True)
 logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
+class MirrorProcessor(FrameProcessor):
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, InputAudioRawFrame):
+            await self.push_frame(OutputAudioRawFrame(
+                audio=frame.audio,
+                sample_rate=frame.sample_rate,
+                num_channels=frame.num_channels)
+            )
+        elif isinstance(frame, InputImageRawFrame):
+            await self.push_frame(OutputImageRawFrame(
+                image=frame.image,
+                size=frame.size,
+                format=frame.format)
+            )
+        else:
+            await self.push_frame(frame, direction)
 
 async def main():
     async with aiohttp.ClientSession() as session:
@@ -52,7 +73,7 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             transport.capture_participant_video(participant["id"])
 
-        pipeline = Pipeline([daily_transport.input(), tk_transport.output()])
+        pipeline = Pipeline([daily_transport.input(), MirrorProcessor(), tk_transport.output()])
 
         task = PipelineTask(pipeline)
 

examples/foundational/11-sound-effects.py

@@ -12,9 +12,9 @@ import wave
 
 from pipecat.frames.frames import (
     Frame,
-    AudioRawFrame,
     LLMFullResponseEndFrame,
     LLMMessagesFrame,
+    OutputAudioRawFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -53,8 +53,8 @@ for file in sound_files:
     filename = os.path.splitext(os.path.basename(full_path))[0]
     # Open the image and convert it to bytes
     with wave.open(full_path) as audio_file:
-        sounds[file] = AudioRawFrame(audio_file.readframes(-1),
-                                     audio_file.getframerate(), audio_file.getnchannels())
+        sounds[file] = OutputAudioRawFrame(audio_file.readframes(-1),
+                                           audio_file.getframerate(), audio_file.getnchannels())
 
 
 class OutboundSoundEffectWrapper(FrameProcessor):