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

examples(15a): use daily transcription instead of local whisper

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-10-24 16:47:41 -07:00
parent cfb48200c2
commit 60c8c2f6e9
1 changed files with 2 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/foundational/15a-switch-languages.py
View File

@@ -10,7 +10,7 @@ import os
import sys import sys
from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame from pipecat.frames.frames import LLMMessagesFrame, TTSUpdateSettingsFrame
from pipecat.pipeline.pipeline import Pipeline from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.parallel_pipeline import ParallelPipeline from pipecat.pipeline.parallel_pipeline import ParallelPipeline
from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.runner import PipelineRunner
@@ -19,7 +19,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.filters.function_filter import FunctionFilter from pipecat.processors.filters.function_filter import FunctionFilter
from pipecat.services.cartesia import CartesiaTTSService from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.openai import OpenAILLMService from pipecat.services.openai import OpenAILLMService
from pipecat.services.whisper import Model, WhisperSTTService
from pipecat.transports.services.daily import DailyParams, DailyTransport from pipecat.transports.services.daily import DailyParams, DailyTransport
from openai.types.chat import ChatCompletionToolParam from openai.types.chat import ChatCompletionToolParam
@@ -61,16 +60,14 @@ async def main():
token, token,
"Pipecat", "Pipecat",
DailyParams( DailyParams(
audio_in_enabled=True,
audio_out_enabled=True, audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True, vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(), vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True, vad_audio_passthrough=True,
), ),
) )
stt = WhisperSTTService(model=Model.LARGE)
english_tts = CartesiaTTSService( english_tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"), api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
@@ -116,7 +113,6 @@ 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
ParallelPipeline( # TTS (bot will speak the chosen language) ParallelPipeline( # TTS (bot will speak the chosen language)