From 41eef5efc4b59c01e17db36a5a327f9421a878c9 Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Tue, 13 Jan 2026 11:36:15 -0500 Subject: [PATCH] Add 07j Gladia VAD foundational example, add to release evals --- .../07j-interruptible-gladia-vad.py | 140 ++++++++++++++++++ scripts/evals/run-release-evals.py | 1 + 2 files changed, 141 insertions(+) create mode 100644 examples/foundational/07j-interruptible-gladia-vad.py diff --git a/examples/foundational/07j-interruptible-gladia-vad.py b/examples/foundational/07j-interruptible-gladia-vad.py new file mode 100644 index 000000000..7f2790611 --- /dev/null +++ b/examples/foundational/07j-interruptible-gladia-vad.py @@ -0,0 +1,140 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + + +import os + +from dotenv import load_dotenv +from loguru import logger + +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_context import LLMContext +from pipecat.processors.aggregators.llm_response_universal import ( + LLMContextAggregatorPair, + LLMUserAggregatorParams, +) +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.cartesia.tts import CartesiaTTSService +from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig +from pipecat.services.gladia.stt import GladiaSTTService +from pipecat.services.openai.llm import OpenAILLMService +from pipecat.transcriptions.language import Language +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams +from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams +from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies + +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. +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + ), + "twilio": lambda: FastAPIWebsocketParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + ), +} + + +async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): + logger.info(f"Starting bot") + + stt = GladiaSTTService( + api_key=os.getenv("GLADIA_API_KEY", ""), + region=os.getenv("GLADIA_REGION"), + params=GladiaInputParams( + language_config=LanguageConfig( + languages=[Language.EN], + ), + enable_vad=True, + ), + ) + + tts = CartesiaTTSService( + api_key=os.getenv("CARTESIA_API_KEY", ""), + voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ) + + llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", "")) + + messages = [ + { + "role": "system", + "content": f"You are a helpful LLM. 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, + user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()), + ) + + 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, + ), + idle_timeout_secs=runner_args.pipeline_idle_timeout_secs, + ) + + @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."}) + 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(handle_sigint=runner_args.handle_sigint) + await runner.run(task) + + +async def bot(runner_args: RunnerArguments): + """Main bot entry point compatible with Pipecat Cloud.""" + transport = await create_transport(runner_args, transport_params) + await run_bot(transport, runner_args) + + +if __name__ == "__main__": + from pipecat.runner.run import main + + main() diff --git a/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py index 65902f41a..21c38a20e 100644 --- a/scripts/evals/run-release-evals.py +++ b/scripts/evals/run-release-evals.py @@ -112,6 +112,7 @@ TESTS_07 = [ ("07g-interruptible-openai.py", EVAL_SIMPLE_MATH), ("07h-interruptible-openpipe.py", EVAL_SIMPLE_MATH), ("07j-interruptible-gladia.py", EVAL_SIMPLE_MATH), + ("07j-interruptible-gladia-vad.py", EVAL_SIMPLE_MATH), ("07k-interruptible-lmnt.py", EVAL_SIMPLE_MATH), ("07l-interruptible-groq.py", EVAL_SIMPLE_MATH), ("07m-interruptible-aws.py", EVAL_SIMPLE_MATH),