Add Soniox STT service

This commit is contained in:
Matej Marinko
2025-05-28 09:35:21 +02:00
parent 0a39769cd0
commit 2968c846ce
10 changed files with 617 additions and 2 deletions

View File

@@ -0,0 +1,115 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.soniox.config import SonioxInputParams
from pipecat.services.soniox.stt import SonioxSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
load_dotenv(override=True)
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
logger.info(f"Starting bot")
transport = SmallWebRTCTransport(
webrtc_connection=webrtc_connection,
params=TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
stt = SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
params=SonioxInputParams(
# Add language hints to improve transcription accuracy. Variants are ignored.
# For example "en-GB" will be treated same as "en".
# List of supported languages: https://soniox.com/docs/speech-to-text/core-concepts/supported-languages
language_hints=[Language.EN, Language.ES, Language.JA, Language.ZH],
),
)
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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
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(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=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": "Please introduce yourself to the user."})
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
if __name__ == "__main__":
from run import main
main()

View File

@@ -0,0 +1,77 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
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.services.soniox.config import SonioxInputParams
from pipecat.services.soniox.stt import SonioxSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
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}")
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
logger.info(f"Starting bot")
transport = SmallWebRTCTransport(
webrtc_connection=webrtc_connection,
params=TransportParams(audio_in_enabled=True),
)
stt = SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
params=SonioxInputParams(
# Add language hints to improve transcription accuracy. Variants are ignored.
# For example "en-GB" will be treated same as "en".
# List of supported languages: https://soniox.com/docs/speech-to-text/core-concepts/supported-languages
language_hints=[Language.EN, Language.ES, Language.JA, Language.ZH],
),
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(pipeline)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
if __name__ == "__main__":
from run import main
main()