Merge pull request #183 from pipecat-ai/khk-deepgram-fix

moving Deepgram TTS base_url from beta to prod

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- Fixed Deepgram Aura TTS base_url and added ErrorFrame reporting.
 - GoogleLLMService `api_key` argument is now mandatory.
 
 ### Fixed

examples/foundational/07c-interruptible-deepgram.py

@@ -0,0 +1,94 @@
+#
+# 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 PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.deepgram import DeepgramTTSService
+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,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = DeepgramTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            voice="aura-helios-en"
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4-turbo-preview")
+
+        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, 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/deepgram.py

@@ -8,7 +8,7 @@
 
 from typing import AsyncGenerator
 
-from pipecat.frames.frames import AudioRawFrame, Frame
+from pipecat.frames.frames import AudioRawFrame, ErrorFrame, Frame
 from pipecat.services.ai_services import TTSService
 
 from loguru import logger
@@ -21,7 +21,7 @@ def __init__(
             *,
             aiohttp_session: aiohttp.ClientSession,
             api_key: str,
-            voice: str = "alpha-asteria-en-v2",
+            voice: str = "aura-helios-en",
             **kwargs):
         super().__init__(**kwargs)
 
@@ -31,11 +31,18 @@ def __init__(
 
     async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
         logger.info(f"Running Deepgram TTS for {text}")
-        base_url = "https://api.beta.deepgram.com/v1/speak"
+        base_url = "https://api.deepgram.com/v1/speak"
         request_url = f"{base_url}?model={self._voice}&encoding=linear16&container=none&sample_rate=16000"
         headers = {"authorization": f"token {self._api_key}"}
         body = {"text": text}
+
         async with self._aiohttp_session.post(request_url, headers=headers, json=body) as r:
+            if r.status != 200:
+                text = await r.text()
+                logger.error(f"Error getting audio (status: {r.status}, error: {text})")
+                yield ErrorFrame(f"Error getting audio (status: {r.status}, error: {text})")
+                return
+
             async for data in r.content:
                 frame = AudioRawFrame(audio=data, sample_rate=16000, num_channels=1)
                 yield frame