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

Add an example for Whisper using OpenAI API

Browse Source
This commit is contained in:
Jin Kim
2025-02-04 10:32:55 +09:00
parent 823b763b25
commit ef1e4277d3
1 changed files with 12 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/foundational/07g-interruptible-openai.py
View File

@@ -18,7 +18,7 @@ from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.openai import OpenAILLMService, OpenAITTSService from pipecat.services.openai import OpenAILLMService, OpenAISTTService, OpenAITTSService
from pipecat.transports.services.daily import DailyParams, DailyTransport from pipecat.transports.services.daily import DailyParams, DailyTransport
load_dotenv(override=True) load_dotenv(override=True)
@@ -38,12 +38,21 @@ async def main():
DailyParams( DailyParams(
audio_out_enabled=True, audio_out_enabled=True,
audio_out_sample_rate=24000, audio_out_sample_rate=24000,
transcription_enabled=True, transcription_enabled=False,
vad_enabled=True, vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(), vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,
), ),
) )
# You can use the OpenAI compatible API like Groq.
# stt = OpenAISTTService(
# base_url="https://api.groq.com/openai/v1",
# api_key="gsk_***",
# model="whisper-large-v3",
# )
stt = OpenAISTTService(api_key=os.getenv("OPENAI_API_KEY"), model="whisper-1")
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="alloy") tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="alloy")
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o") llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -61,6 +70,7 @@ async def main():
pipeline = Pipeline( pipeline = Pipeline(
[ [
transport.input(), # Transport user input transport.input(), # Transport user input
stt, # STT
context_aggregator.user(), # User responses context_aggregator.user(), # User responses
llm, # LLM llm, # LLM
tts, # TTS tts, # TTS