Merge pull request #53 from daily-co/fix_other_joined_event

Don't do time-consuming processing in `on_other_joined_event`

src/dailyai/services/fal_ai_services.py

@@ -32,7 +32,7 @@ class FalImageGenService(ImageGenService):
     async def run_image_gen(self, sentence) -> tuple[str, bytes]:
         def get_image_url(sentence, size):
             handler = fal.apps.submit(
-                # "110602490-fast-sdxl",
+                #"110602490-fast-sdxl",
                 "fal-ai/fast-sdxl",
                 arguments={"prompt": sentence},
             )

src/examples/foundational/01-say-one-thing.py

@@ -28,21 +28,31 @@ async def main(room_url):
             voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
         )
 
+        other_joined_event = asyncio.Event()
+        participant_name = ''
+
+        async def say_hello():
+            nonlocal tts
+            nonlocal participant_name
+
+            await other_joined_event.wait()
+            await tts.say(
+                "Hello there, " + participant_name + "!",
+                transport.send_queue,
+            )
+            await transport.stop_when_done()
+
         # Register an event handler so we can play the audio when the participant joins.
         @transport.event_handler("on_participant_joined")
         async def on_participant_joined(transport, participant):
             if participant["info"]["isLocal"]:
                 return
 
-            await tts.say(
+            nonlocal participant_name
-                "Hello there, " + participant["info"]["userName"] + "!",
+            participant_name = participant["info"]["userName"] or ''
-                transport.send_queue,
+            other_joined_event.set()
-            )
 
-            # wait for the output queue to be empty, then leave the meeting
+        await asyncio.gather(transport.run(), say_hello())
-            await transport.stop_when_done()
-
-        await transport.run()
         del tts
 
 

src/examples/foundational/02-llm-say-one-thing.py

@@ -42,15 +42,20 @@ async def main(room_url):
             }
         ]
 
-        @transport.event_handler("on_first_other_participant_joined")
+        other_joined_event = asyncio.Event()
-        async def on_first_other_participant_joined(transport):
+        async def speak_from_llm():
+            await other_joined_event.wait()
             await tts.run_to_queue(
                 transport.send_queue,
-                llm.run([LLMMessagesQueueFrame(messages)]),
+                llm.run([LLMMessagesQueueFrame(messages)])
             )
             await transport.stop_when_done()
 
-        await transport.run()
+        @transport.event_handler("on_first_other_participant_joined")
+        async def on_first_other_participant_joined(transport):
+            other_joined_event.set()
+
+        await asyncio.gather(transport.run(), speak_from_llm())
 
 
 if __name__ == "__main__":

src/examples/foundational/03-still-frame.py

@@ -23,6 +23,7 @@ async def main(room_url):
             camera_enabled=True,
             camera_width=1024,
             camera_height=1024,
+            duration_minutes=1
         )
 
         imagegen = FalImageGenService(
@@ -32,13 +33,19 @@ async def main(room_url):
             key_secret=os.getenv("FAL_KEY_SECRET"),
         )
 
-        @transport.event_handler("on_first_other_participant_joined")
+        other_joined_event = asyncio.Event()
-        async def on_first_other_participant_joined(transport):
+
+        async def show_image():
+            await other_joined_event.wait()
             await imagegen.run_to_queue(
                 transport.send_queue, [TextFrame("a cat in the style of picasso")]
             )
 
-        await transport.run()
+        @transport.event_handler("on_first_other_participant_joined")
+        async def on_first_other_participant_joined(transport):
+            other_joined_event.set()
+
+        await asyncio.gather(transport.run(), show_image())
 
 
 if __name__ == "__main__":

src/examples/foundational/04-utterance-and-speech.py

@@ -62,8 +62,15 @@ async def main(room_url: str):
         await source_queue.put(EndFrame())
         pipeline_run_task = pipeline.run_pipeline()
 
+        other_participant_joined = asyncio.Event()
+
         @transport.event_handler("on_first_other_participant_joined")
         async def on_first_other_participant_joined(transport):
+            other_participant_joined.set()
+
+        async def say_something():
+            await other_participant_joined.wait()
+
             await azure_tts.say(
                 "My friend the LLM is now going to tell a joke about llamas.",
                 transport.send_queue,
@@ -87,9 +94,8 @@ async def main(room_url: str):
                         break
 
             await asyncio.gather(pipeline_run_task, buffer_to_send_queue())
-            await transport.stop_when_done()
 
-        await transport.run()
+        await asyncio.gather(transport.run(), say_something())
 
 
 if __name__ == "__main__":

src/examples/foundational/05-sync-speech-and-image.py

@@ -140,12 +140,18 @@ async def main(room_url):
         )
         pipeline_task = pipeline.run_pipeline()
 
+        other_joined = asyncio.Event()
+
         @transport.event_handler("on_first_other_participant_joined")
         async def on_first_other_participant_joined(transport):
+            other_joined.set()
+
+        async def show_calendar():
+            await other_joined.wait()
             await pipeline_task
             await transport.stop_when_done()
 
-        await transport.run()
+        await asyncio.gather(transport.run(), show_calendar())
 
 
 if __name__ == "__main__":

src/examples/foundational/06-listen-and-respond.py

@@ -49,7 +49,7 @@ async def main(room_url: str, token):
         async def on_first_other_participant_joined(transport):
             await tts.say("Hi, I'm listening!", transport.send_queue)
 
-        async def handle_transcriptions():
+        async def have_conversation():
             messages = [
                 {
                     "role": "system",
@@ -75,7 +75,7 @@ async def main(room_url: str, token):
 
         transport.transcription_settings["extra"]["endpointing"] = True
         transport.transcription_settings["extra"]["punctuate"] = True
-        await asyncio.gather(transport.run(), handle_transcriptions())
+        await asyncio.gather(transport.run(), have_conversation())
 
 
 if __name__ == "__main__":