Add foundational examples for AssemblyAI u3-rt-pro
- 07o-interruptible-assemblyai.py: Basic example using Pipecat VAD mode - 07o-interruptible-assemblyai-stt.py: Advanced example using STT-controlled turn detection with comprehensive documentation on u3-rt-pro features (turn detection tuning, prompt-based enhancement, speaker diarization)
This commit is contained in:
zack
175
examples/foundational/07o-interruptible-assemblyai-stt.py
Normal file
175
examples/foundational/07o-interruptible-assemblyai-stt.py
Normal file
@@ -0,0 +1,175 @@
|
||||
#
|
||||
# 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.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.assemblyai.models import AssemblyAIConnectionParams
|
||||
from pipecat.services.assemblyai.stt import AssemblyAISTTService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
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 use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"""AssemblyAI u3-rt-pro STT Example with STT-Controlled Turn Detection
|
||||
|
||||
This example demonstrates using AssemblyAI's u3-rt-pro Speech-to-Text model
|
||||
with STT-controlled turn detection for more natural conversation flow.
|
||||
|
||||
Key features:
|
||||
|
||||
1. STT-Controlled Turn Detection
|
||||
- Set `vad_force_turn_endpoint=False` to enable STT mode
|
||||
- AssemblyAI's model determines when user starts/stops speaking
|
||||
- Uses `ExternalUserTurnStrategies` instead of Pipecat's VAD
|
||||
- More natural turn detection based on speech patterns and pauses
|
||||
|
||||
2. Advanced Turn Detection Tuning (STT Mode)
|
||||
- `min_end_of_turn_silence_when_confident`: Minimum silence (ms) when confident
|
||||
about end-of-turn. Lower values = faster responses. Default: 200ms
|
||||
- `max_turn_silence`: Maximum silence (ms) before forcing end-of-turn.
|
||||
Prevents long pauses. Default: 1000ms
|
||||
|
||||
3. Prompt-Based Transcription Enhancement
|
||||
- Use `prompt` parameter to improve accuracy for specific names/terms
|
||||
- Particularly useful for proper nouns, technical terms, domain vocabulary
|
||||
- Example: "Names: Xiomara, Saoirse, Krzystof. Technical terms: API, OAuth."
|
||||
|
||||
4. Speaker Diarization (Optional)
|
||||
- Enable with `speaker_labels=True`
|
||||
- Automatically identifies different speakers in multi-party conversations
|
||||
- TranscriptionFrame includes speaker_id field (e.g., "Speaker A", "Speaker B")
|
||||
|
||||
5. Language Detection (Optional, multilingual model only)
|
||||
- Enable with `language_detection=True`
|
||||
- Automatically detects spoken language
|
||||
- Available with universal-streaming-multilingual model
|
||||
|
||||
For more information: https://www.assemblyai.com/docs/speech-to-text/streaming
|
||||
"""
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AssemblyAISTTService(
|
||||
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
|
||||
vad_force_turn_endpoint=False, # Enable STT-controlled turn detection
|
||||
connection_params=AssemblyAIConnectionParams(
|
||||
speech_model="u3-rt-pro",
|
||||
# Optional: Tune turn detection timing (defaults shown below)
|
||||
# min_end_of_turn_silence_when_confident=100, # Default
|
||||
# max_turn_silence=1000, # Default
|
||||
# Optional: Boost accuracy for specific names/terms
|
||||
# prompt="Names: Xiomara, Saoirse, Krzystof. Technical terms: API, OAuth.",
|
||||
# Optional: Enable speaker diarization
|
||||
# speaker_labels=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": "You are a helpful LLM in a WebRTC call. 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)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
user_aggregator, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # 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()
|
||||
Reference in New Issue
Block a user