Merge pull request #3838 from pipecat-ai/mb/remove-playht
Remove PlayHT TTS services
This commit is contained in:
Mark Backman
26
README.md
26
README.md
@@ -81,19 +81,19 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
||||
| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) |
|
||||
| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
| Category | Services |
|
||||
| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
||||
| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) |
|
||||
| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||
|
||||
|
||||
1
changelog/3838.removed.md
Normal file
1
changelog/3838.removed.md
Normal file
@@ -0,0 +1 @@
|
||||
- ⚠️ Removed `PlayHTTTSService` and `PlayHTHttpTTSService`. PlayHT has been shut down and is no longer available.
|
||||
@@ -42,7 +42,7 @@ This script:
|
||||
|
||||
- Creates a fresh virtual environment
|
||||
- Installs all dependencies as specified in requirements files
|
||||
- Handles conflicting dependencies (like grpcio versions for Riva and PlayHT)
|
||||
- Handles conflicting dependencies (like grpcio versions for Riva)
|
||||
- Builds the documentation in an isolated environment
|
||||
- Provides detailed logging of the build process
|
||||
|
||||
@@ -74,7 +74,6 @@ start _build/html/index.html
|
||||
├── index.rst # Main documentation entry point
|
||||
├── requirements-base.txt # Base documentation dependencies
|
||||
├── requirements-riva.txt # Riva-specific dependencies
|
||||
├── requirements-playht.txt # PlayHT-specific dependencies
|
||||
├── build-docs.sh # Local build script
|
||||
└── rtd-test.py # ReadTheDocs test build script
|
||||
```
|
||||
|
||||
@@ -147,10 +147,6 @@ KOALA_ACCESS_KEY=...
|
||||
# Piper
|
||||
PIPER_BASE_URL=...
|
||||
|
||||
# PlayHT
|
||||
PLAYHT_USER_ID=...
|
||||
PLAYHT_API_KEY=...
|
||||
|
||||
# Plivo
|
||||
PLIVO_AUTH_ID=...
|
||||
PLIVO_AUTH_TOKEN=...
|
||||
|
||||
@@ -1,125 +0,0 @@
|
||||
#
|
||||
# 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.vad.silero import SileroVADAnalyzer
|
||||
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.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTHttpTTSService
|
||||
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 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 = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = PlayHTHttpTTSService(
|
||||
user_id=os.getenv("PLAYHT_USER_ID"),
|
||||
api_key=os.getenv("PLAYHT_API_KEY"),
|
||||
voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
|
||||
)
|
||||
|
||||
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(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
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()
|
||||
@@ -1,127 +0,0 @@
|
||||
#
|
||||
# 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.vad.silero import SileroVADAnalyzer
|
||||
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.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTTTSService
|
||||
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
|
||||
|
||||
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 = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = PlayHTTTSService(
|
||||
user_id=os.getenv("PLAYHT_USER_ID"),
|
||||
api_key=os.getenv("PLAYHT_API_KEY"),
|
||||
voice_url="s3://voice-cloning-zero-shot/e46b4027-b38d-4d24-b292-38fbca2be0ef/original/manifest.json",
|
||||
params=PlayHTTTSService.InputParams(language=Language.EN),
|
||||
)
|
||||
|
||||
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(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
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()
|
||||
@@ -1,126 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
|
||||
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.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTTTSService, PlayHTTTSSettings
|
||||
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)
|
||||
|
||||
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 = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = PlayHTTTSService(
|
||||
api_key=os.getenv("PLAYHT_API_KEY"),
|
||||
user_id=os.getenv("PLAYHT_USER_ID"),
|
||||
voice_url=os.getenv("PLAYHT_VOICE_URL", ""),
|
||||
)
|
||||
|
||||
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(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_aggregator,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
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")
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
await asyncio.sleep(10)
|
||||
logger.info("Updating PlayHT TTS settings: speed=1.3")
|
||||
await task.queue_frame(TTSUpdateSettingsFrame(delta=PlayHTTTSSettings(speed=1.3)))
|
||||
|
||||
@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()
|
||||
@@ -100,7 +100,6 @@ openpipe = [ "openpipe>=4.50.0,<6" ]
|
||||
openrouter = []
|
||||
perplexity = []
|
||||
piper = [ "piper-tts>=1.3.0,<2", "requests>=2.32.5,<3" ]
|
||||
playht = [ "pipecat-ai[websockets-base]" ]
|
||||
qwen = []
|
||||
remote-smart-turn = []
|
||||
resembleai = [ "pipecat-ai[websockets-base]" ]
|
||||
|
||||
@@ -1,13 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import sys
|
||||
|
||||
from pipecat.services import DeprecatedModuleProxy
|
||||
|
||||
from .tts import *
|
||||
|
||||
sys.modules[__name__] = DeprecatedModuleProxy(globals(), "playht", "playht.tts")
|
||||
@@ -1,699 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""PlayHT text-to-speech service implementations.
|
||||
|
||||
This module provides integration with PlayHT's text-to-speech API
|
||||
supporting both WebSocket streaming and HTTP-based synthesis.
|
||||
"""
|
||||
|
||||
import io
|
||||
import json
|
||||
import struct
|
||||
import uuid
|
||||
import warnings
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, AsyncGenerator, Optional
|
||||
|
||||
import aiohttp
|
||||
from loguru import logger
|
||||
from pydantic import BaseModel
|
||||
|
||||
from pipecat.frames.frames import (
|
||||
CancelFrame,
|
||||
EndFrame,
|
||||
ErrorFrame,
|
||||
Frame,
|
||||
InterruptionFrame,
|
||||
StartFrame,
|
||||
TTSAudioRawFrame,
|
||||
TTSStartedFrame,
|
||||
TTSStoppedFrame,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection
|
||||
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
|
||||
from pipecat.services.tts_service import InterruptibleTTSService, TTSService
|
||||
from pipecat.transcriptions.language import Language, resolve_language
|
||||
from pipecat.utils.tracing.service_decorators import traced_tts
|
||||
|
||||
try:
|
||||
from websockets.asyncio.client import connect as websocket_connect
|
||||
from websockets.protocol import State
|
||||
except ModuleNotFoundError as e:
|
||||
logger.error(f"Exception: {e}")
|
||||
logger.error("In order to use PlayHTTTSService, you need to `pip install pipecat-ai[playht]`.")
|
||||
raise Exception(f"Missing module: {e}")
|
||||
|
||||
|
||||
def language_to_playht_language(language: Language) -> Optional[str]:
|
||||
"""Convert a Language enum to PlayHT language code.
|
||||
|
||||
Args:
|
||||
language: The Language enum value to convert.
|
||||
|
||||
Returns:
|
||||
The corresponding PlayHT language code, or None if not supported.
|
||||
"""
|
||||
LANGUAGE_MAP = {
|
||||
Language.AF: "afrikans",
|
||||
Language.AM: "amharic",
|
||||
Language.AR: "arabic",
|
||||
Language.BN: "bengali",
|
||||
Language.BG: "bulgarian",
|
||||
Language.CA: "catalan",
|
||||
Language.CS: "czech",
|
||||
Language.DA: "danish",
|
||||
Language.DE: "german",
|
||||
Language.EL: "greek",
|
||||
Language.EN: "english",
|
||||
Language.ES: "spanish",
|
||||
Language.FR: "french",
|
||||
Language.GL: "galician",
|
||||
Language.HE: "hebrew",
|
||||
Language.HI: "hindi",
|
||||
Language.HR: "croatian",
|
||||
Language.HU: "hungarian",
|
||||
Language.ID: "indonesian",
|
||||
Language.IT: "italian",
|
||||
Language.JA: "japanese",
|
||||
Language.KO: "korean",
|
||||
Language.MS: "malay",
|
||||
Language.NL: "dutch",
|
||||
Language.PL: "polish",
|
||||
Language.PT: "portuguese",
|
||||
Language.RU: "russian",
|
||||
Language.SQ: "albanian",
|
||||
Language.SR: "serbian",
|
||||
Language.SV: "swedish",
|
||||
Language.TH: "thai",
|
||||
Language.TL: "tagalog",
|
||||
Language.TR: "turkish",
|
||||
Language.UK: "ukrainian",
|
||||
Language.UR: "urdu",
|
||||
Language.XH: "xhosa",
|
||||
Language.ZH: "mandarin",
|
||||
}
|
||||
|
||||
return resolve_language(language, LANGUAGE_MAP, use_base_code=False)
|
||||
|
||||
|
||||
@dataclass
|
||||
class PlayHTTTSSettings(TTSSettings):
|
||||
"""Settings for PlayHT TTS services.
|
||||
|
||||
Parameters:
|
||||
output_format: Audio output format.
|
||||
voice_engine: Voice engine to use.
|
||||
speed: Speech speed multiplier. Defaults to 1.0.
|
||||
seed: Random seed for voice consistency.
|
||||
playht_sample_rate: Audio sample rate sent to the API.
|
||||
"""
|
||||
|
||||
output_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
|
||||
voice_engine: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
|
||||
speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
|
||||
seed: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
|
||||
playht_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
|
||||
|
||||
|
||||
class PlayHTTTSService(InterruptibleTTSService):
|
||||
"""PlayHT WebSocket-based text-to-speech service.
|
||||
|
||||
.. deprecated:: 0.0.88
|
||||
|
||||
This class is deprecated and will be removed in a future version.
|
||||
PlayHT is shutting down their API on December 31st, 2025.
|
||||
|
||||
Provides real-time text-to-speech synthesis using PlayHT's WebSocket API.
|
||||
Supports streaming audio generation with configurable voice engines and
|
||||
language settings.
|
||||
"""
|
||||
|
||||
_settings: PlayHTTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
"""Input parameters for PlayHT TTS configuration.
|
||||
|
||||
Parameters:
|
||||
language: Language for synthesis. Defaults to English.
|
||||
speed: Speech speed multiplier. Defaults to 1.0.
|
||||
seed: Random seed for voice consistency.
|
||||
"""
|
||||
|
||||
language: Optional[Language] = Language.EN
|
||||
speed: Optional[float] = 1.0
|
||||
seed: Optional[int] = None
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
api_key: str,
|
||||
user_id: str,
|
||||
voice_url: str,
|
||||
voice_engine: str = "Play3.0-mini",
|
||||
sample_rate: Optional[int] = None,
|
||||
output_format: str = "wav",
|
||||
params: Optional[InputParams] = None,
|
||||
**kwargs,
|
||||
):
|
||||
"""Initialize the PlayHT WebSocket TTS service.
|
||||
|
||||
Args:
|
||||
api_key: PlayHT API key for authentication.
|
||||
user_id: PlayHT user ID for authentication.
|
||||
voice_url: URL of the voice to use for synthesis.
|
||||
voice_engine: Voice engine to use. Defaults to "Play3.0-mini".
|
||||
sample_rate: Audio sample rate. If None, uses default.
|
||||
output_format: Audio output format. Defaults to "wav".
|
||||
params: Additional input parameters for voice customization.
|
||||
**kwargs: Additional arguments passed to parent InterruptibleTTSService.
|
||||
"""
|
||||
super().__init__(
|
||||
pause_frame_processing=True,
|
||||
sample_rate=sample_rate,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("always")
|
||||
warnings.warn(
|
||||
"PlayHT is shutting down their API on December 31st, 2025. "
|
||||
"'PlayHTTTSService' is deprecated and will be removed in a future version.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
params = params or PlayHTTTSService.InputParams()
|
||||
|
||||
self._api_key = api_key
|
||||
self._user_id = user_id
|
||||
self._websocket_url = None
|
||||
self._receive_task = None
|
||||
self._context_id = None
|
||||
|
||||
self._settings = PlayHTTTSSettings(
|
||||
model=voice_engine,
|
||||
voice=voice_url,
|
||||
language=self.language_to_service_language(params.language)
|
||||
if params.language
|
||||
else "english",
|
||||
output_format=output_format,
|
||||
voice_engine=voice_engine,
|
||||
speed=params.speed,
|
||||
seed=params.seed,
|
||||
playht_sample_rate=0,
|
||||
)
|
||||
self._sync_model_name_to_metrics()
|
||||
|
||||
def can_generate_metrics(self) -> bool:
|
||||
"""Check if this service can generate processing metrics.
|
||||
|
||||
Returns:
|
||||
True, as PlayHT service supports metrics generation.
|
||||
"""
|
||||
return True
|
||||
|
||||
async def _update_settings(self, delta: TTSSettings) -> dict[str, Any]:
|
||||
"""Apply a settings delta.
|
||||
|
||||
Settings are stored but not applied to the active connection.
|
||||
"""
|
||||
changed = await super()._update_settings(delta)
|
||||
|
||||
if not changed:
|
||||
return changed
|
||||
|
||||
# TODO: someday we could reconnect here to apply updated settings.
|
||||
# Code might look something like the below:
|
||||
# await self._disconnect()
|
||||
# await self._connect()
|
||||
|
||||
self._warn_unhandled_updated_settings(changed)
|
||||
|
||||
return changed
|
||||
|
||||
def language_to_service_language(self, language: Language) -> Optional[str]:
|
||||
"""Convert a Language enum to PlayHT service language format.
|
||||
|
||||
Args:
|
||||
language: The language to convert.
|
||||
|
||||
Returns:
|
||||
The PlayHT-specific language code, or None if not supported.
|
||||
"""
|
||||
return language_to_playht_language(language)
|
||||
|
||||
async def start(self, frame: StartFrame):
|
||||
"""Start the PlayHT TTS service.
|
||||
|
||||
Args:
|
||||
frame: The start frame containing initialization parameters.
|
||||
"""
|
||||
await super().start(frame)
|
||||
await self._connect()
|
||||
|
||||
async def stop(self, frame: EndFrame):
|
||||
"""Stop the PlayHT TTS service.
|
||||
|
||||
Args:
|
||||
frame: The end frame.
|
||||
"""
|
||||
await super().stop(frame)
|
||||
await self._disconnect()
|
||||
|
||||
async def cancel(self, frame: CancelFrame):
|
||||
"""Cancel the PlayHT TTS service.
|
||||
|
||||
Args:
|
||||
frame: The cancel frame.
|
||||
"""
|
||||
await super().cancel(frame)
|
||||
await self._disconnect()
|
||||
|
||||
async def _connect(self):
|
||||
"""Connect to PlayHT WebSocket and start receive task."""
|
||||
await super()._connect()
|
||||
|
||||
await self._connect_websocket()
|
||||
|
||||
if self._websocket and not self._receive_task:
|
||||
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
|
||||
|
||||
async def _disconnect(self):
|
||||
"""Disconnect from PlayHT WebSocket and clean up tasks."""
|
||||
await super()._disconnect()
|
||||
|
||||
if self._receive_task:
|
||||
await self.cancel_task(self._receive_task)
|
||||
self._receive_task = None
|
||||
|
||||
await self._disconnect_websocket()
|
||||
|
||||
async def _connect_websocket(self):
|
||||
"""Connect to PlayHT websocket."""
|
||||
try:
|
||||
if self._websocket and self._websocket.state is State.OPEN:
|
||||
return
|
||||
|
||||
logger.debug("Connecting to PlayHT")
|
||||
|
||||
if not self._websocket_url:
|
||||
await self._get_websocket_url()
|
||||
|
||||
if not isinstance(self._websocket_url, str):
|
||||
raise ValueError("WebSocket URL is not a string")
|
||||
|
||||
self._websocket = await websocket_connect(self._websocket_url)
|
||||
|
||||
await self._call_event_handler("on_connected")
|
||||
except ValueError as e:
|
||||
logger.error(f"{self} initialization error: {e}")
|
||||
self._websocket = None
|
||||
await self._call_event_handler("on_connection_error", f"{e}")
|
||||
except Exception as e:
|
||||
await self.push_error(error_msg=f"Error connecting: {e}", exception=e)
|
||||
self._websocket = None
|
||||
await self._call_event_handler("on_connection_error", f"{e}")
|
||||
|
||||
async def _disconnect_websocket(self):
|
||||
"""Disconnect from PlayHT websocket."""
|
||||
try:
|
||||
await self.stop_all_metrics()
|
||||
|
||||
if self._websocket:
|
||||
logger.debug("Disconnecting from PlayHT")
|
||||
await self._websocket.close()
|
||||
except Exception as e:
|
||||
await self.push_error(error_msg=f"Error disconnecting: {e}", exception=e)
|
||||
finally:
|
||||
self._context_id = None
|
||||
self._websocket = None
|
||||
await self._call_event_handler("on_disconnected")
|
||||
|
||||
async def _get_websocket_url(self):
|
||||
"""Retrieve WebSocket URL from PlayHT API."""
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.post(
|
||||
"https://api.play.ht/api/v4/websocket-auth",
|
||||
headers={
|
||||
"Authorization": f"Bearer {self._api_key}",
|
||||
"X-User-Id": self._user_id,
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
) as response:
|
||||
if response.status in (200, 201):
|
||||
data = await response.json()
|
||||
# Handle the new response format with multiple URLs
|
||||
if "websocket_urls" in data:
|
||||
# Select URL based on voice_engine
|
||||
if self._settings.voice_engine in data["websocket_urls"]:
|
||||
self._websocket_url = data["websocket_urls"][
|
||||
self._settings.voice_engine
|
||||
]
|
||||
else:
|
||||
raise ValueError(
|
||||
f"Unsupported voice engine: {self._settings.voice_engine}"
|
||||
)
|
||||
else:
|
||||
raise ValueError("Invalid response: missing websocket_urls")
|
||||
else:
|
||||
raise Exception(f"Failed to get WebSocket URL: {response.status}")
|
||||
|
||||
def _get_websocket(self):
|
||||
"""Get the WebSocket connection if available."""
|
||||
if self._websocket:
|
||||
return self._websocket
|
||||
raise Exception("Websocket not connected")
|
||||
|
||||
def create_context_id(self) -> str:
|
||||
"""Generate a unique context ID for a TTS request in case we don't have one already in progress.
|
||||
|
||||
Returns:
|
||||
A unique string identifier for the TTS context.
|
||||
"""
|
||||
# If a context ID does not exist, create a new one.
|
||||
# If an ID exists, continue using the current ID.
|
||||
# When interruptions happen, user speech results in
|
||||
# an interruption, which resets the context ID.
|
||||
if not self._context_id:
|
||||
return str(uuid.uuid4())
|
||||
return self._context_id
|
||||
|
||||
async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
|
||||
"""Handle interruption by stopping metrics and clearing request ID."""
|
||||
await super()._handle_interruption(frame, direction)
|
||||
await self.stop_all_metrics()
|
||||
self._context_id = None
|
||||
|
||||
async def _receive_messages(self):
|
||||
"""Receive messages from PlayHT websocket."""
|
||||
async for message in self._get_websocket():
|
||||
if isinstance(message, bytes):
|
||||
# Skip the WAV header message
|
||||
if message.startswith(b"RIFF"):
|
||||
continue
|
||||
await self.stop_ttfb_metrics()
|
||||
frame = TTSAudioRawFrame(message, self.sample_rate, 1, context_id=self._context_id)
|
||||
await self.push_frame(frame)
|
||||
else:
|
||||
logger.debug(f"Received text message: {message}")
|
||||
try:
|
||||
msg = json.loads(message)
|
||||
if msg.get("type") == "start":
|
||||
# Handle start of stream
|
||||
logger.debug(f"Started processing request: {msg.get('request_id')}")
|
||||
elif msg.get("type") == "end":
|
||||
# Handle end of stream
|
||||
if "request_id" in msg and msg["request_id"] == self._context_id:
|
||||
await self.push_frame(TTSStoppedFrame(context_id=self._context_id))
|
||||
self._context_id = None
|
||||
elif "error" in msg:
|
||||
await self.push_error(error_msg=f"Error: {msg['error']}")
|
||||
except json.JSONDecodeError:
|
||||
logger.error(f"Invalid JSON message: {message}")
|
||||
|
||||
@traced_tts
|
||||
async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:
|
||||
"""Generate TTS audio from text using PlayHT's WebSocket API.
|
||||
|
||||
Args:
|
||||
text: The text to synthesize into speech.
|
||||
context_id: The context ID for tracking audio frames.
|
||||
|
||||
Yields:
|
||||
Frame: Audio frames containing the synthesized speech.
|
||||
"""
|
||||
logger.debug(f"{self}: Generating TTS [{text}]")
|
||||
|
||||
try:
|
||||
# Reconnect if the websocket is closed
|
||||
if not self._websocket or self._websocket.state is State.CLOSED:
|
||||
await self._connect()
|
||||
|
||||
if not self._context_id:
|
||||
await self.start_ttfb_metrics()
|
||||
yield TTSStartedFrame(context_id=context_id)
|
||||
self._context_id = context_id
|
||||
|
||||
tts_command = {
|
||||
"text": text,
|
||||
"voice": self._settings.voice,
|
||||
"voice_engine": self._settings.voice_engine,
|
||||
"output_format": self._settings.output_format,
|
||||
"sample_rate": self.sample_rate,
|
||||
"language": self._settings.language,
|
||||
"speed": self._settings.speed,
|
||||
"seed": self._settings.seed,
|
||||
"request_id": self._context_id,
|
||||
}
|
||||
|
||||
try:
|
||||
await self._get_websocket().send(json.dumps(tts_command))
|
||||
await self.start_tts_usage_metrics(text)
|
||||
except Exception as e:
|
||||
yield ErrorFrame(error=f"Unknown error occurred: {e}")
|
||||
yield TTSStoppedFrame(context_id=context_id)
|
||||
await self._disconnect()
|
||||
await self._connect()
|
||||
return
|
||||
|
||||
# The actual audio frames will be handled in _receive_task_handler
|
||||
yield None
|
||||
|
||||
except Exception as e:
|
||||
yield ErrorFrame(error=f"Unknown error occurred: {e}")
|
||||
|
||||
|
||||
class PlayHTHttpTTSService(TTSService):
|
||||
"""PlayHT HTTP-based text-to-speech service.
|
||||
|
||||
.. deprecated:: 0.0.88
|
||||
|
||||
This class is deprecated and will be removed in a future version.
|
||||
PlayHT is shutting down their API on December 31st, 2025.
|
||||
|
||||
Provides text-to-speech synthesis using PlayHT's HTTP API for simpler,
|
||||
non-streaming synthesis. Suitable for use cases where streaming is not
|
||||
required and simpler integration is preferred.
|
||||
"""
|
||||
|
||||
_settings: PlayHTTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
"""Input parameters for PlayHT HTTP TTS configuration.
|
||||
|
||||
Parameters:
|
||||
language: Language for synthesis. Defaults to English.
|
||||
speed: Speech speed multiplier. Defaults to 1.0.
|
||||
seed: Random seed for voice consistency.
|
||||
"""
|
||||
|
||||
language: Optional[Language] = Language.EN
|
||||
speed: Optional[float] = 1.0
|
||||
seed: Optional[int] = None
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
api_key: str,
|
||||
user_id: str,
|
||||
voice_url: str,
|
||||
voice_engine: str = "Play3.0-mini",
|
||||
protocol: Optional[str] = None,
|
||||
output_format: str = "wav",
|
||||
sample_rate: Optional[int] = None,
|
||||
params: Optional[InputParams] = None,
|
||||
**kwargs,
|
||||
):
|
||||
"""Initialize the PlayHT HTTP TTS service.
|
||||
|
||||
Args:
|
||||
api_key: PlayHT API key for authentication.
|
||||
user_id: PlayHT user ID for authentication.
|
||||
voice_url: URL of the voice to use for synthesis.
|
||||
voice_engine: Voice engine to use. Defaults to "Play3.0-mini".
|
||||
protocol: Protocol to use ("http" or "ws").
|
||||
|
||||
.. deprecated:: 0.0.80
|
||||
This parameter no longer has any effect and will be removed in a future version.
|
||||
Use PlayHTTTSService for WebSocket or PlayHTHttpTTSService for HTTP.
|
||||
|
||||
output_format: Audio output format. Defaults to "wav".
|
||||
sample_rate: Audio sample rate. If None, uses default.
|
||||
params: Additional input parameters for voice customization.
|
||||
**kwargs: Additional arguments passed to parent TTSService.
|
||||
"""
|
||||
super().__init__(sample_rate=sample_rate, **kwargs)
|
||||
|
||||
# Warn about deprecated protocol parameter if explicitly provided
|
||||
if protocol:
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("always")
|
||||
warnings.warn(
|
||||
"The 'protocol' parameter is deprecated and will be removed in a future version.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("always")
|
||||
warnings.warn(
|
||||
"PlayHT is shutting down their API on December 31st, 2025. "
|
||||
"'PlayHTHttpTTSService' is deprecated and will be removed in a future version.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
|
||||
params = params or PlayHTHttpTTSService.InputParams()
|
||||
|
||||
self._user_id = user_id
|
||||
self._api_key = api_key
|
||||
|
||||
# Check if voice_engine contains protocol information (backward compatibility)
|
||||
if "-http" in voice_engine:
|
||||
# Extract the base engine name
|
||||
voice_engine = voice_engine.replace("-http", "")
|
||||
elif "-ws" in voice_engine:
|
||||
# Extract the base engine name
|
||||
voice_engine = voice_engine.replace("-ws", "")
|
||||
|
||||
self._settings = PlayHTTTSSettings(
|
||||
model=voice_engine,
|
||||
voice=voice_url,
|
||||
language=self.language_to_service_language(params.language)
|
||||
if params.language
|
||||
else "english",
|
||||
output_format=output_format,
|
||||
voice_engine=voice_engine,
|
||||
speed=params.speed,
|
||||
seed=params.seed,
|
||||
playht_sample_rate=0,
|
||||
)
|
||||
self._sync_model_name_to_metrics()
|
||||
|
||||
async def start(self, frame: StartFrame):
|
||||
"""Start the PlayHT HTTP TTS service.
|
||||
|
||||
Args:
|
||||
frame: The start frame containing initialization parameters.
|
||||
"""
|
||||
await super().start(frame)
|
||||
self._settings.playht_sample_rate = self.sample_rate
|
||||
|
||||
def can_generate_metrics(self) -> bool:
|
||||
"""Check if this service can generate processing metrics.
|
||||
|
||||
Returns:
|
||||
True, as PlayHT HTTP service supports metrics generation.
|
||||
"""
|
||||
return True
|
||||
|
||||
def language_to_service_language(self, language: Language) -> Optional[str]:
|
||||
"""Convert a Language enum to PlayHT service language format.
|
||||
|
||||
Args:
|
||||
language: The language to convert.
|
||||
|
||||
Returns:
|
||||
The PlayHT-specific language code, or None if not supported.
|
||||
"""
|
||||
return language_to_playht_language(language)
|
||||
|
||||
@traced_tts
|
||||
async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:
|
||||
"""Generate TTS audio from text using PlayHT's HTTP API.
|
||||
|
||||
Args:
|
||||
text: The text to synthesize into speech.
|
||||
context_id: The context ID for tracking audio frames.
|
||||
|
||||
Yields:
|
||||
Frame: Audio frames containing the synthesized speech.
|
||||
"""
|
||||
logger.debug(f"{self}: Generating TTS [{text}]")
|
||||
|
||||
try:
|
||||
await self.start_ttfb_metrics()
|
||||
|
||||
# Prepare the request payload
|
||||
payload = {
|
||||
"text": text,
|
||||
"voice": self._settings.voice,
|
||||
"voice_engine": self._settings.voice_engine,
|
||||
"output_format": self._settings.output_format,
|
||||
"sample_rate": self.sample_rate,
|
||||
"language": self._settings.language,
|
||||
}
|
||||
|
||||
# Add optional parameters if they exist
|
||||
if self._settings.speed is not None:
|
||||
payload["speed"] = self._settings.speed
|
||||
if self._settings.seed is not None:
|
||||
payload["seed"] = self._settings.seed
|
||||
|
||||
headers = {
|
||||
"Authorization": f"Bearer {self._api_key}",
|
||||
"X-User-Id": self._user_id,
|
||||
"Content-Type": "application/json",
|
||||
"Accept": "*/*",
|
||||
}
|
||||
|
||||
await self.start_tts_usage_metrics(text)
|
||||
|
||||
yield TTSStartedFrame(context_id=context_id)
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
async with session.post(
|
||||
"https://api.play.ht/api/v2/tts/stream",
|
||||
headers=headers,
|
||||
json=payload,
|
||||
) as response:
|
||||
if response.status not in (200, 201):
|
||||
error_text = await response.text()
|
||||
raise Exception(f"PlayHT API error {response.status}: {error_text}")
|
||||
|
||||
in_header = True
|
||||
buffer = b""
|
||||
|
||||
CHUNK_SIZE = self.chunk_size
|
||||
|
||||
async for chunk in response.content.iter_chunked(CHUNK_SIZE):
|
||||
if len(chunk) == 0:
|
||||
continue
|
||||
|
||||
# Skip the RIFF header
|
||||
if in_header:
|
||||
buffer += chunk
|
||||
if len(buffer) <= 36:
|
||||
continue
|
||||
else:
|
||||
fh = io.BytesIO(buffer)
|
||||
fh.seek(36)
|
||||
(data, size) = struct.unpack("<4sI", fh.read(8))
|
||||
while data != b"data":
|
||||
fh.read(size)
|
||||
(data, size) = struct.unpack("<4sI", fh.read(8))
|
||||
# Extract audio data after header
|
||||
audio_data = buffer[fh.tell() :]
|
||||
if len(audio_data) > 0:
|
||||
await self.stop_ttfb_metrics()
|
||||
frame = TTSAudioRawFrame(
|
||||
audio_data, self.sample_rate, 1, context_id=context_id
|
||||
)
|
||||
yield frame
|
||||
in_header = False
|
||||
elif len(chunk) > 0:
|
||||
await self.stop_ttfb_metrics()
|
||||
frame = TTSAudioRawFrame(
|
||||
chunk, self.sample_rate, 1, context_id=context_id
|
||||
)
|
||||
yield frame
|
||||
|
||||
except Exception as e:
|
||||
yield ErrorFrame(error=f"Unknown error occurred: {e}")
|
||||
finally:
|
||||
await self.stop_ttfb_metrics()
|
||||
yield TTSStoppedFrame(context_id=context_id)
|
||||
6
uv.lock
generated
6
uv.lock
generated
@@ -4550,9 +4550,6 @@ piper = [
|
||||
{ name = "piper-tts" },
|
||||
{ name = "requests" },
|
||||
]
|
||||
playht = [
|
||||
{ name = "websockets" },
|
||||
]
|
||||
resembleai = [
|
||||
{ name = "websockets" },
|
||||
]
|
||||
@@ -4722,7 +4719,6 @@ requires-dist = [
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'lmnt'" },
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'neuphonic'" },
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'openai'" },
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'playht'" },
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'resembleai'" },
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'rime'" },
|
||||
{ name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'sarvam'" },
|
||||
@@ -4763,7 +4759,7 @@ requires-dist = [
|
||||
{ name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1" },
|
||||
{ name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" },
|
||||
]
|
||||
provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "playht", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"]
|
||||
provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"]
|
||||
|
||||
[package.metadata.requires-dev]
|
||||
dev = [
|
||||
|
||||
Reference in New Issue
Block a user