diff --git a/CHANGELOG.md b/CHANGELOG.md index 74fde759b..6efebf31a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Added +- Added a new `DeepgramHttpTTSService`, which delivers a meaningful reduction + in latency when compared to the `DeepgramTTSService`. + - Add support for `speaking_rate` input parameter in `GoogleHttpTTSService`. - Added `enable_speaker_diarization` and `enable_language_identification` to diff --git a/examples/foundational/07c-interruptible-deepgram-http.py b/examples/foundational/07c-interruptible-deepgram-http.py new file mode 100644 index 000000000..c444b5638 --- /dev/null +++ b/examples/foundational/07c-interruptible-deepgram-http.py @@ -0,0 +1,132 @@ +# +# Copyright (c) 2024–2025, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + + +import os + +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_context import LLMContext +from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.deepgram.stt import DeepgramSTTService +from pipecat.services.deepgram.tts import DeepgramHttpTTSService +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 + +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)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), + "twilio": lambda: FastAPIWebsocketParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), +} + + +async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): + logger.info(f"Starting bot") + + async with aiohttp.ClientSession() as session: + stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) + + tts = DeepgramHttpTTSService( + api_key=os.getenv("DEEPGRAM_API_KEY"), + voice="aura-2-andromeda-en", + aiohttp_session=session, + ) + + 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 = 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, + ), + 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 ce0a32dd6..5c66dd75d 100644 --- a/scripts/evals/run-release-evals.py +++ b/scripts/evals/run-release-evals.py @@ -87,6 +87,7 @@ TESTS_07 = [ ("07b-interruptible-langchain.py", EVAL_SIMPLE_MATH), ("07c-interruptible-deepgram.py", EVAL_SIMPLE_MATH), ("07c-interruptible-deepgram-flux.py", EVAL_SIMPLE_MATH), + ("07c-interruptible-deepgram-http.py", EVAL_SIMPLE_MATH), ("07d-interruptible-elevenlabs.py", EVAL_SIMPLE_MATH), ("07d-interruptible-elevenlabs-http.py", EVAL_SIMPLE_MATH), ("07f-interruptible-azure.py", EVAL_SIMPLE_MATH), diff --git a/src/pipecat/services/deepgram/tts.py b/src/pipecat/services/deepgram/tts.py index 5819e4123..f3869c0ba 100644 --- a/src/pipecat/services/deepgram/tts.py +++ b/src/pipecat/services/deepgram/tts.py @@ -12,6 +12,7 @@ for generating speech from text using various voice models. from typing import AsyncGenerator, Optional +import aiohttp from loguru import logger from pipecat.frames.frames import ( @@ -117,3 +118,114 @@ class DeepgramTTSService(TTSService): except Exception as e: logger.exception(f"{self} exception: {e}") yield ErrorFrame(f"Error getting audio: {str(e)}") + + +class DeepgramHttpTTSService(TTSService): + """Deepgram HTTP text-to-speech service. + + Provides text-to-speech synthesis using Deepgram's HTTP TTS API. + Supports various voice models and audio encoding formats with + configurable sample rates and quality settings. + """ + + def __init__( + self, + *, + api_key: str, + voice: str = "aura-2-helena-en", + aiohttp_session: aiohttp.ClientSession, + base_url: str = "https://api.deepgram.com", + sample_rate: Optional[int] = None, + encoding: str = "linear16", + **kwargs, + ): + """Initialize the Deepgram TTS service. + + Args: + api_key: Deepgram API key for authentication. + voice: Voice model to use for synthesis. Defaults to "aura-2-helena-en". + aiohttp_session: Shared aiohttp session for HTTP requests with connection pooling. + base_url: Custom base URL for Deepgram API. Defaults to "https://api.deepgram.com". + sample_rate: Audio sample rate in Hz. If None, uses service default. + encoding: Audio encoding format. Defaults to "linear16". + **kwargs: Additional arguments passed to parent TTSService class. + """ + super().__init__(sample_rate=sample_rate, **kwargs) + + self._api_key = api_key + self._session = aiohttp_session + self._base_url = base_url + self._settings = { + "encoding": encoding, + } + self.set_voice(voice) + + def can_generate_metrics(self) -> bool: + """Check if the service can generate metrics. + + Returns: + True, as Deepgram TTS service supports metrics generation. + """ + return True + + @traced_tts + async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]: + """Generate speech from text using Deepgram's TTS API. + + Args: + text: The text to synthesize into speech. + + Yields: + Frame: Audio frames containing the synthesized speech, plus start/stop frames. + """ + logger.debug(f"{self}: Generating TTS [{text}]") + + # Build URL with parameters + url = f"{self._base_url}/v1/speak" + + headers = {"Authorization": f"Token {self._api_key}", "Content-Type": "application/json"} + + params = { + "model": self._voice_id, + "encoding": self._settings["encoding"], + "sample_rate": self.sample_rate, + "container": "none", + } + + payload = { + "text": text, + } + + try: + await self.start_ttfb_metrics() + + async with self._session.post( + url, headers=headers, json=payload, params=params + ) as response: + if response.status != 200: + error_text = await response.text() + raise Exception(f"HTTP {response.status}: {error_text}") + + await self.start_tts_usage_metrics(text) + yield TTSStartedFrame() + + CHUNK_SIZE = self.chunk_size + + first_chunk = True + async for chunk in response.content.iter_chunked(CHUNK_SIZE): + if first_chunk: + await self.stop_ttfb_metrics() + first_chunk = False + + if chunk: + yield TTSAudioRawFrame( + audio=chunk, + sample_rate=self.sample_rate, + num_channels=1, + ) + + yield TTSStoppedFrame() + + except Exception as e: + logger.exception(f"{self} exception: {e}") + yield ErrorFrame(f"Error getting audio: {str(e)}")