Restructured STT and enabled prosody tags for generative Polly

2025-04-04 05:39:08 +00:00
parent 05ae8d3ffa
commit f014f718eb
3 changed files with 638 additions and 617 deletions
--- a/examples/foundational/07m-interruptible-aws.py
+++ b/examples/foundational/07m-interruptible-aws.py
@@ -0,0 +1,113 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
+from pipecat.services.aws.llm import BedrockLLMService, BedrockLLMContext
+from pipecat.services.aws.stt import TranscribeSTTService
+from pipecat.services.aws.tts import PollyTTSService
+
+load_dotenv(override=True)
+
+
+async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
+    logger.info(f"Starting bot")
+
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
+
+    stt = TranscribeSTTService()
+
+    tts = PollyTTSService(
+        region="us-west-2",  # only specific regions support generative TTS
+        voice_id="Joanna",
+        params=PollyTTSService.InputParams(
+            engine="generative",
+            language=Language.EN_US,
+            rate="1.1"
+        ),
+    )
+
+    llm = BedrockLLMService(
+        aws_region="us-west-2",
+        model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
+        params=BedrockLLMService.InputParams(
+            temperature=0.8,
+            latency="optimized"
+        )
+    )
+
+    messages = [
+            {
+                "role": "system",
+                "content": [{"text": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way."}],
+            },
+        ]
+    )
+
+    context = BedrockLLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+         ]
+     )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
+
+    @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": "user", "content": [{"text": "Please introduce yourself to the user."}]})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from run import main
+
+    main()