azure tts ttfb

examples/foundational/07f-interruptible-azure-tts.py

@@ -0,0 +1,95 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.azure import AzureTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main(room_url: str, token):
+    async with aiohttp.ClientSession() as session:
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                audio_out_sample_rate=16000,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"),
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+
+        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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append(
+                {"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    (url, token) = configure()
+    asyncio.run(main(url, token))

src/pipecat/services/azure.py

@@ -7,6 +7,7 @@
 import aiohttp
 import asyncio
 import io
+import time
 
 from PIL import Image
 from typing import AsyncGenerator
@@ -46,6 +47,8 @@ class AzureTTSService(TTSService):
         self._voice = voice
 
     async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
+        start_time = time.time()
+        ttfb = None
         logger.debug(f"Generating TTS: {text}")
 
         ssml = (
@@ -61,6 +64,9 @@ class AzureTTSService(TTSService):
         result = await asyncio.to_thread(self.speech_synthesizer.speak_ssml, (ssml))
 
         if result.reason == ResultReason.SynthesizingAudioCompleted:
+            if ttfb is None:
+                ttfb = time.time() - start_time
+                logger.debug(f"TTS ttfb: {ttfb}")
             # Azure always sends a 44-byte header. Strip it off.
             yield AudioRawFrame(audio=result.audio_data[44:], sample_rate=16000, num_channels=1)
         elif result.reason == ResultReason.Canceled: