transports(daily): always check size of read audio frames

CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to **pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Fixed
+
+- Fixed a Daily transport blocking situation that occurred while reading audio
+  frames after a participant left the room. Needs daily-python >= 0.10.1.
+
 ## [0.0.32] - 2024-06-22
 
 ### Added

pyproject.toml

@@ -37,7 +37,7 @@ Website = "https://pipecat.ai"
 anthropic = [ "anthropic~=0.25.7" ]
 azure = [ "azure-cognitiveservices-speech~=1.37.0" ]
 cartesia = [ "numpy~=1.26.0", "sounddevice", "cartesia" ]
-daily = [ "daily-python~=0.10.0" ]
+daily = [ "daily-python~=0.10.1" ]
 deepgram = [ "deepgram-sdk~=3.2.7" ]
 examples = [ "python-dotenv~=1.0.0", "flask~=3.0.3", "flask_cors~=4.0.1" ]
 fal = [ "fal-client~=0.4.0" ]

src/pipecat/transports/base_input.py

@@ -55,7 +55,7 @@ class BaseInputTransport(FrameProcessor):
 
     async def push_audio_frame(self, frame: AudioRawFrame):
         if self._params.audio_in_enabled or self._params.vad_enabled:
-            self._audio_in_queue.put_nowait(frame)
+            await self._audio_in_queue.put(frame)
 
     #
     # Frame processor

src/pipecat/transports/services/daily.py

@@ -209,19 +209,18 @@ class DailyTransportClient(EventHandler):
     async def read_next_audio_frame(self) -> AudioRawFrame | None:
         sample_rate = self._params.audio_in_sample_rate
         num_channels = self._params.audio_in_channels
+        num_frames = int(sample_rate / 100) * 2  # 20ms of audio
 
-        if self._other_participant_has_joined:
-            num_frames = int(sample_rate / 100) * 2  # 20ms of audio
-
-            future = self._loop.create_future()
-            self._speaker.read_frames(num_frames, completion=completion_callback(future))
-            audio = await future
+        future = self._loop.create_future()
+        self._speaker.read_frames(num_frames, completion=completion_callback(future))
+        audio = await future
 
+        if len(audio) > 0:
             return AudioRawFrame(audio=audio, sample_rate=sample_rate, num_channels=num_channels)
         else:
-            # If no one has ever joined the meeting `read_frames()` would block,
-            # instead we just wait a bit. daily-python should probably return
-            # silence instead.
+            # If we don't read any audio it could be there's no participant
+            # connected. daily-python will return immediately if that's the
+            # case, so let's sleep for a little bit (i.e. busy wait).
             await asyncio.sleep(0.01)
             return None