HeyGen implementation for Pipecat - HeyGenTransport.

2025-09-24 14:33:56 -03:00
parent 463752360b
commit f6164e3bde
7 changed files with 510 additions and 4 deletions
--- a/examples/foundational/43-heygen-transport.py
+++ b/examples/foundational/43-heygen-transport.py
@@ -0,0 +1,113 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+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_universal import (
+    LLMContext,
+    LLMContextAggregatorPair,
+)
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.transports.heygen.transport import HeyGenParams, HeyGenTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        transport = HeyGenTransport(
+            api_key=os.getenv("HEYGEN_API_KEY"),
+            session=session,
+            params=HeyGenParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+                turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="00967b2f-88a6-4a31-8153-110a92134b9f",
+        )
+
+        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful assistant. Your output will be converted to audio so don't include special characters in your answers. Be succinct and respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = LLMContext(messages)
+        context_aggregator = LLMContextAggregatorPair(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(
+                enable_metrics=True,
+                enable_usage_metrics=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": "system",
+                    "content": "Start by saying 'Hello' and then a short greeting.",
+                }
+            )
+            await task.queue_frames([LLMRunFrame()])
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())