Merge pull request #3656 from pipecat-ai/mb/openai-realtime-stt
Add OpenAIRealtimeSTTService
This commit is contained in:
Mark Backman
135
examples/foundational/07g-interruptible-openai-http.py
Normal file
135
examples/foundational/07g-interruptible-openai-http.py
Normal file
@@ -0,0 +1,135 @@
|
||||
#
|
||||
# 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.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_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.openai.llm import OpenAILLMService
|
||||
from pipecat.services.openai.stt import OpenAISTTService
|
||||
from pipecat.services.openai.tts import OpenAITTSService
|
||||
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_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
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):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = OpenAISTTService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o-transcribe",
|
||||
prompt="Expect words related to dogs, such as breed names.",
|
||||
)
|
||||
|
||||
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are very knowledgable about dogs. 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=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
),
|
||||
)
|
||||
|
||||
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(
|
||||
audio_out_sample_rate=24000,
|
||||
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()
|
||||
@@ -25,8 +25,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.openai.stt import OpenAISTTService
|
||||
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
|
||||
from pipecat.services.openai.tts import OpenAITTSService
|
||||
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
|
||||
@@ -56,10 +57,15 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = OpenAISTTService(
|
||||
stt = OpenAIRealtimeSTTService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o-transcribe",
|
||||
prompt="Expect words related to dogs, such as breed names.",
|
||||
language=Language.EN,
|
||||
# Uses local VAD by default.
|
||||
# To enable server-side VAD, set turn_detection=None or
|
||||
# a dict with server_vad settings.
|
||||
# turn_detection={"type": "server_vad", "threshold": 0.5},
|
||||
)
|
||||
|
||||
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
|
||||
|
||||
@@ -18,7 +18,7 @@ from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
|
||||
from pipecat.services.elevenlabs.stt import ElevenLabsRealtimeSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
@@ -51,29 +51,25 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = ElevenLabsSTTService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
aiohttp_session=session,
|
||||
)
|
||||
stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
|
||||
|
||||
tl = TranscriptionLogger()
|
||||
tl = TranscriptionLogger()
|
||||
|
||||
pipeline = Pipeline([transport.input(), stt, tl])
|
||||
pipeline = Pipeline([transport.input(), stt, tl])
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
@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)
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
|
||||
88
examples/foundational/13m-openai-transcription.py
Normal file
88
examples/foundational/13m-openai-transcription.py
Normal file
@@ -0,0 +1,88 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import Frame, TranscriptionFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class TranscriptionLogger(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, TranscriptionFrame):
|
||||
print(f"Transcription: {frame.text}")
|
||||
|
||||
# Push all frames through
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# 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, vad_analyzer=SileroVADAnalyzer()),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
|
||||
),
|
||||
"webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = OpenAIRealtimeSTTService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o-transcribe",
|
||||
prompt="Expect words related to dogs, such as breed names.",
|
||||
)
|
||||
|
||||
tl = TranscriptionLogger()
|
||||
|
||||
pipeline = Pipeline([transport.input(), stt, tl])
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@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