From 17edfe98bd51ef71b9df435ae8c4be62656643bc Mon Sep 17 00:00:00 2001 From: Chad Bailey Date: Thu, 22 Feb 2024 22:16:41 +0000 Subject: [PATCH] more tweaks --- src/dailyai/services/ai_services.py | 1 - .../06c-listen-respond-interruptible-refactor.py | 16 +++++++++------- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/src/dailyai/services/ai_services.py b/src/dailyai/services/ai_services.py index bb8f3429f..386b1b951 100644 --- a/src/dailyai/services/ai_services.py +++ b/src/dailyai/services/ai_services.py @@ -147,7 +147,6 @@ class TTSService(AIService): if text: async for audio_chunk in self.run_tts(text): - print(f"audio chunk size: {len(audio_chunk)}") size = 8000 for i in range(0, len(audio_chunk), size): yield AudioQueueFrame(audio_chunk[i : i+size]) diff --git a/src/examples/foundational/06c-listen-respond-interruptible-refactor.py b/src/examples/foundational/06c-listen-respond-interruptible-refactor.py index db6c38c31..e5a4762b1 100644 --- a/src/examples/foundational/06c-listen-respond-interruptible-refactor.py +++ b/src/examples/foundational/06c-listen-respond-interruptible-refactor.py @@ -8,6 +8,7 @@ from dailyai.services.daily_transport_service import DailyTransportService from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService from dailyai.services.open_ai_services import OpenAILLMService +from dailyai.services.deepgram_ai_services import DeepgramTTSService from dailyai.services.ai_services import FrameLogger from dailyai.services.groq_ai_services import GroqLLMService @@ -44,13 +45,14 @@ async def main(room_url: str, token): llm = OpenAILLMService( context=context, api_key=os.getenv("OPENAI_CHATGPT_API_KEY")) # llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), context=context) - 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=os.getenv("ELEVENLABS_VOICE_ID")) + # 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=os.getenv("ELEVENLABS_VOICE_ID")) + # tts = DeepgramTTSService(aiohttp_session=session, api_key=os.getenv("DEEPGRAM_API_KEY"), voice=os.getenv("DEEPGRAM_VOICE")) fl = FrameLogger("just outside the innermost layer") async def run_response(in_frame):