WIP

src/dailyai/services/base_transport_service.py

@@ -176,13 +176,19 @@ class BaseTransportService():
         self._logger.info("🎬 Starting frame consumer thread")
         b = bytearray()
         smallest_write_size = 3200
+        largest_write_size = 8000
         all_audio_frames = bytearray()
         while True:
             try:
                 frames_or_frame: QueueFrame | list[QueueFrame] = (
                     self._threadsafe_send_queue.get()
                 )
-                if isinstance(frames_or_frame, QueueFrame):
+                if isinstance(frames_or_frame, AudioQueueFrame) and len(frames_or_frame.data) > largest_write_size:
+                    # subdivide large audio frames to enable interruption
+                    frames = []
+                    for i in range(0, len(frames_or_frame.data), largest_write_size):
+                        frames.append(AudioQueueFrame(frames_or_frame.data[i : i+largest_write_size]))
+                elif isinstance(frames_or_frame, QueueFrame):
                     frames: list[QueueFrame] = [frames_or_frame]
                 elif isinstance(frames_or_frame, list):
                     frames: list[QueueFrame] = frames_or_frame
@@ -190,6 +196,7 @@ class BaseTransportService():
                     raise Exception("Unknown type in output queue")
 
                 for frame in frames:
+                    print(f"got frame of type: {type(frame)}")
                     if isinstance(frame, EndStreamQueueFrame):
                         self._logger.info("Stopping frame consumer thread")
                         self._threadsafe_send_queue.task_done()

src/examples/foundational/06b-patient-intake.py

@@ -7,6 +7,7 @@ from typing import AsyncGenerator
 from dailyai.services.daily_transport_service import DailyTransportService
 from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
 from dailyai.services.open_ai_services import OpenAILLMService
+from dailyai.services.deepgram_ai_services import DeepgramTTSService
 from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
 from dailyai.queue_aggregators import LLMAssistantContextAggregator, LLMContextAggregator, LLMUserContextAggregator
 from support.runner import configure
@@ -261,7 +262,8 @@ async def main(room_url: str, token):
         # tts = AzureTTSService(api_key=os.getenv(
         #     "AZURE_SPEECH_API_KEY"), region=os.getenv("AZURE_SPEECH_REGION"))
         tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv(
-            "ELEVENLABS_API_KEY"), voice_id="EXAVITQu4vr4xnSDxMaL")
+            "ELEVENLABS_API_KEY"), voice_id="XrExE9yKIg1WjnnlVkGX") # matilda
+        # tts = DeepgramTTSService(aiohttp_session=session, api_key=os.getenv("DEEPGRAM_API_KEY"), voice=os.getenv("DEEPGRAM_VOICE")) 
         messages = [
         ]
         tma_in = LLMUserContextAggregator(