wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

WIP

Browse Source
This commit is contained in:
Chad Bailey
2024-02-28 15:18:03 -06:00
parent 1f9c5d132f
commit d6108dae5c
2 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/dailyai/services/base_transport_service.py
View File

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

4
src/examples/foundational/06b-patient-intake.py
View File

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