Merge branch 'main' into krisp-viva-vad-support

examples/foundational/07p-interruptible-krisp-viva.py

@@ -28,10 +28,11 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.filters.krisp_viva_filter import KrispVivaFilter
-from pipecat.audio.turn.krisp_viva_turn import KrispTurnParams, KrispVivaTurn
+from pipecat.audio.turn.krisp_viva_turn import KrispVivaTurn
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
+from pipecat.metrics.metrics import TurnMetricsData
+from pipecat.observers.loggers.metrics_log_observer import MetricsLogObserver
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -42,8 +43,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -53,9 +54,11 @@ from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+
+krisp_viva_filter = KrispVivaFilter()
+
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -83,24 +86,28 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
                 stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=KrispVivaTurn())]
             ),
+            vad_analyzer=SileroVADAnalyzer(),
         ),
     )
 
@@ -108,11 +115,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -123,13 +130,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_usage_metrics=True,
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        observers=[MetricsLogObserver(include_metrics={TurnMetricsData})],
     )
 
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")