add speechmatics tts

This commit is contained in:
Aaron Ng
2025-10-29 14:53:20 +00:00
parent 493d6bf91e
commit 4050e8b7dc
3 changed files with 217 additions and 30 deletions

View File

@@ -20,10 +20,10 @@ from pipecat.processors.aggregators.llm_response import (
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.elevenlabs.tts import ElevenLabsTTSService
from pipecat.services.openai.base_llm import BaseOpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -51,35 +51,41 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
"""Speechmatics STT Service Example
"""Speechmatics STT and TTS Service Example
This example demonstrates using Speechmatics Speech-to-Text service with speaker diarization and intelligent speaker management. Key features:
This example demonstrates using Speechmatics Speech-to-Text and Text-to-Speech services
with speaker diarization and intelligent speaker management. Key features:
1. Speaker Diarization
1. Speaker Diarization (STT)
- Automatically identifies and distinguishes between different speakers
- First speaker is identified as 'S1', others get subsequent IDs
- Uses `enable_diarization` parameter to manage speaker detection
2. Smart Speaker Control
2. Smart Speaker Control (STT)
- `focus_speakers` parameter lets you target specific speakers (e.g. ["S1"])
- Other speakers will be wrapped in PASSIVE tags
- Only processes speech from focused speakers
- Words from all speakers are wrapped with XML tags for clear speaker identification
- Other speakers' speech only sent when focused speaker is active
3. Voice Activity Detection
3. Voice Activity Detection (STT)
- Built-in VAD using `enable_vad` parameter
- Remove `vad_analyzer` from `transport` config to use module's VAD
- Emits speaker started/stopped events
4. Configuration Options
4. Text-to-Speech (TTS)
- Low latency streaming audio synthesis
- Multiple voice options available including `sarah`, `theo`, and `megan`
5. Configuration Options
- `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
- Configurable `end_of_utterance_silence_trigger` (default 0.5s)
- Customizable speaker formatting
- Additional diarization settings available
For detailed information about operating points and configuration:
https://docs.speechmatics.com/rt-api-ref
For detailed information:
- STT: https://docs.speechmatics.com/rt-api-ref
- TTS: https://docs.speechmatics.com/text-to-speech/quickstart
"""
logger.info(f"Starting bot")
@@ -97,10 +103,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
),
)
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY"),
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
model="eleven_turbo_v2_5",
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsTTSService.InputParams(
voice="sarah",
),
)
llm = OpenAILLMService(
@@ -112,7 +119,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
{
"role": "system",
"content": (
"You are a helpful British assistant called Alfred. "
"You are a helpful British assistant called Sarah. "
"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. "
"Always include punctuation in your responses. "