Merge pull request #4031 from niczy/xai-tts-service
Add xAI TTS service
This commit is contained in:
Mark Backman
28
README.md
28
README.md
@@ -85,20 +85,20 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
|||||||
|
|
||||||
## 🧩 Available services
|
## 🧩 Available services
|
||||||
|
|
||||||
| Category | 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), [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) |
|
| 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), [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), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [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), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
| 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), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [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), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [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), [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), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
| 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), [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), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [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), |
|
| 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 |
|
| 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) |
|
| 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), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [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) |
|
| 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) |
|
| 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) |
|
| 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) |
|
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||||
| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) |
|
| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) |
|
||||||
|
|
||||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||||
|
|
||||||
|
|||||||
1
changelog/4031.added.md
Normal file
1
changelog/4031.added.md
Normal file
@@ -0,0 +1 @@
|
|||||||
|
- Added `XAIHttpTTSService` for text-to-speech using xAI's HTTP TTS API.
|
||||||
@@ -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.anthropic.llm import AnthropicLLMService
|
|
||||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
|
||||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
||||||
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 = CartesiaTTSService(
|
|
||||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
|
||||||
settings=CartesiaTTSService.Settings(
|
|
||||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
|
||||||
),
|
|
||||||
)
|
|
||||||
|
|
||||||
llm = AnthropicLLMService(
|
|
||||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
|
||||||
settings=AnthropicLLMService.Settings(
|
|
||||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
|
||||||
),
|
|
||||||
)
|
|
||||||
|
|
||||||
context = LLMContext()
|
|
||||||
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.
|
|
||||||
context.add_message(
|
|
||||||
{"role": "developer", "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()
|
|
||||||
128
examples/foundational/07e-interruptible-xai.py
Normal file
128
examples/foundational/07e-interruptible-xai.py
Normal file
@@ -0,0 +1,128 @@
|
|||||||
|
#
|
||||||
|
# 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 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.grok.llm import GrokLLMService
|
||||||
|
from pipecat.services.xai.tts import XAIHttpTTSService
|
||||||
|
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")
|
||||||
|
|
||||||
|
async with aiohttp.ClientSession() as session:
|
||||||
|
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||||
|
|
||||||
|
tts = XAIHttpTTSService(
|
||||||
|
api_key=os.getenv("GROK_API_KEY"),
|
||||||
|
aiohttp_session=session,
|
||||||
|
settings=XAIHttpTTSService.Settings(
|
||||||
|
voice="eve",
|
||||||
|
),
|
||||||
|
)
|
||||||
|
|
||||||
|
llm = GrokLLMService(
|
||||||
|
api_key=os.getenv("GROK_API_KEY"),
|
||||||
|
settings=GrokLLMService.Settings(
|
||||||
|
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||||
|
),
|
||||||
|
)
|
||||||
|
|
||||||
|
context = LLMContext()
|
||||||
|
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.
|
||||||
|
context.add_message(
|
||||||
|
{"role": "developer", "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()
|
||||||
@@ -7,6 +7,7 @@
|
|||||||
|
|
||||||
import os
|
import os
|
||||||
|
|
||||||
|
import aiohttp
|
||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
@@ -24,10 +25,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
|
|||||||
)
|
)
|
||||||
from pipecat.runner.types import RunnerArguments
|
from pipecat.runner.types import RunnerArguments
|
||||||
from pipecat.runner.utils import create_transport
|
from pipecat.runner.utils import create_transport
|
||||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
|
||||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||||
from pipecat.services.grok.llm import GrokLLMService
|
from pipecat.services.grok.llm import GrokLLMService
|
||||||
from pipecat.services.llm_service import FunctionCallParams
|
from pipecat.services.llm_service import FunctionCallParams
|
||||||
|
from pipecat.services.xai.tts import XAIHttpTTSService
|
||||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||||
from pipecat.transports.daily.transport import DailyParams
|
from pipecat.transports.daily.transport import DailyParams
|
||||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||||
@@ -60,83 +61,88 @@ transport_params = {
|
|||||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||||
logger.info(f"Starting bot")
|
logger.info(f"Starting bot")
|
||||||
|
|
||||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
async with aiohttp.ClientSession() as session:
|
||||||
|
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||||
|
|
||||||
tts = CartesiaTTSService(
|
tts = XAIHttpTTSService(
|
||||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
api_key=os.getenv("GROK_API_KEY"),
|
||||||
settings=CartesiaTTSService.Settings(
|
aiohttp_session=session,
|
||||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
settings=XAIHttpTTSService.Settings(
|
||||||
),
|
voice="eve",
|
||||||
)
|
),
|
||||||
|
)
|
||||||
|
|
||||||
llm = GrokLLMService(
|
llm = GrokLLMService(
|
||||||
api_key=os.getenv("GROK_API_KEY"),
|
api_key=os.getenv("GROK_API_KEY"),
|
||||||
settings=GrokLLMService.Settings(
|
settings=GrokLLMService.Settings(
|
||||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||||
),
|
),
|
||||||
)
|
)
|
||||||
# You can also register a function_name of None to get all functions
|
# You can also register a function_name of None to get all functions
|
||||||
# sent to the same callback with an additional function_name parameter.
|
# sent to the same callback with an additional function_name parameter.
|
||||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||||
|
|
||||||
weather_function = FunctionSchema(
|
weather_function = FunctionSchema(
|
||||||
name="get_current_weather",
|
name="get_current_weather",
|
||||||
description="Get the current weather",
|
description="Get the current weather",
|
||||||
properties={
|
properties={
|
||||||
"location": {
|
"location": {
|
||||||
"type": "string",
|
"type": "string",
|
||||||
"description": "The city and state, e.g. San Francisco, CA",
|
"description": "The city and state, e.g. San Francisco, CA",
|
||||||
|
},
|
||||||
|
"format": {
|
||||||
|
"type": "string",
|
||||||
|
"enum": ["celsius", "fahrenheit"],
|
||||||
|
"description": "The temperature unit to use. Infer this from the user's location.",
|
||||||
|
},
|
||||||
},
|
},
|
||||||
"format": {
|
required=["location", "format"],
|
||||||
"type": "string",
|
)
|
||||||
"enum": ["celsius", "fahrenheit"],
|
tools = ToolsSchema(standard_tools=[weather_function])
|
||||||
"description": "The temperature unit to use. Infer this from the user's location.",
|
context = LLMContext(tools=tools)
|
||||||
},
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||||
},
|
context,
|
||||||
required=["location", "format"],
|
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||||
)
|
)
|
||||||
tools = ToolsSchema(standard_tools=[weather_function])
|
|
||||||
context = LLMContext(tools=tools)
|
|
||||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
||||||
context,
|
|
||||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
|
||||||
)
|
|
||||||
|
|
||||||
pipeline = Pipeline(
|
pipeline = Pipeline(
|
||||||
[
|
[
|
||||||
transport.input(),
|
transport.input(),
|
||||||
stt,
|
stt,
|
||||||
user_aggregator,
|
user_aggregator,
|
||||||
llm,
|
llm,
|
||||||
tts,
|
tts,
|
||||||
transport.output(),
|
transport.output(),
|
||||||
assistant_aggregator,
|
assistant_aggregator,
|
||||||
]
|
]
|
||||||
)
|
)
|
||||||
|
|
||||||
task = PipelineTask(
|
task = PipelineTask(
|
||||||
pipeline,
|
pipeline,
|
||||||
params=PipelineParams(
|
params=PipelineParams(
|
||||||
enable_metrics=True,
|
enable_metrics=True,
|
||||||
enable_usage_metrics=True,
|
enable_usage_metrics=True,
|
||||||
),
|
),
|
||||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||||
)
|
)
|
||||||
|
|
||||||
@transport.event_handler("on_client_connected")
|
@transport.event_handler("on_client_connected")
|
||||||
async def on_client_connected(transport, client):
|
async def on_client_connected(transport, client):
|
||||||
logger.info(f"Client connected")
|
logger.info(f"Client connected")
|
||||||
# Kick off the conversation.
|
# Kick off the conversation.
|
||||||
await task.queue_frames([LLMRunFrame()])
|
context.add_message(
|
||||||
|
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||||||
|
)
|
||||||
|
await task.queue_frames([LLMRunFrame()])
|
||||||
|
|
||||||
@transport.event_handler("on_client_disconnected")
|
@transport.event_handler("on_client_disconnected")
|
||||||
async def on_client_disconnected(transport, client):
|
async def on_client_disconnected(transport, client):
|
||||||
logger.info(f"Client disconnected")
|
logger.info(f"Client disconnected")
|
||||||
await task.cancel()
|
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):
|
async def bot(runner_args: RunnerArguments):
|
||||||
|
|||||||
@@ -127,6 +127,7 @@ webrtc = [ "aiortc>=1.14.0,<2", "opencv-python>=4.11.0.86,<5" ]
|
|||||||
websocket = [ "pipecat-ai[websockets-base]", "fastapi>=0.115.6,<1" ]
|
websocket = [ "pipecat-ai[websockets-base]", "fastapi>=0.115.6,<1" ]
|
||||||
websockets-base = [ "websockets>=13.1,<16.0" ]
|
websockets-base = [ "websockets>=13.1,<16.0" ]
|
||||||
whisper = [ "faster-whisper~=1.2.1" ]
|
whisper = [ "faster-whisper~=1.2.1" ]
|
||||||
|
xai = []
|
||||||
|
|
||||||
[dependency-groups]
|
[dependency-groups]
|
||||||
dev = [
|
dev = [
|
||||||
|
|||||||
@@ -108,7 +108,7 @@ TESTS_07 = [
|
|||||||
("07c-interruptible-deepgram-http.py", EVAL_SIMPLE_MATH),
|
("07c-interruptible-deepgram-http.py", EVAL_SIMPLE_MATH),
|
||||||
("07d-interruptible-elevenlabs.py", EVAL_SIMPLE_MATH),
|
("07d-interruptible-elevenlabs.py", EVAL_SIMPLE_MATH),
|
||||||
("07d-interruptible-elevenlabs-http.py", EVAL_SIMPLE_MATH),
|
("07d-interruptible-elevenlabs-http.py", EVAL_SIMPLE_MATH),
|
||||||
("07e-interruptible-anthropic.py", EVAL_SIMPLE_MATH),
|
("07e-interruptible-xai.py", EVAL_SIMPLE_MATH),
|
||||||
("07f-interruptible-azure.py", EVAL_SIMPLE_MATH),
|
("07f-interruptible-azure.py", EVAL_SIMPLE_MATH),
|
||||||
("07f-interruptible-azure-http.py", EVAL_SIMPLE_MATH),
|
("07f-interruptible-azure-http.py", EVAL_SIMPLE_MATH),
|
||||||
("07g-interruptible-openai.py", EVAL_SIMPLE_MATH),
|
("07g-interruptible-openai.py", EVAL_SIMPLE_MATH),
|
||||||
|
|||||||
0
src/pipecat/services/xai/__init__.py
Normal file
0
src/pipecat/services/xai/__init__.py
Normal file
216
src/pipecat/services/xai/tts.py
Normal file
216
src/pipecat/services/xai/tts.py
Normal file
@@ -0,0 +1,216 @@
|
|||||||
|
#
|
||||||
|
# Copyright (c) 2024-2026, Daily
|
||||||
|
#
|
||||||
|
# SPDX-License-Identifier: BSD 2-Clause License
|
||||||
|
#
|
||||||
|
|
||||||
|
"""xAI text-to-speech service implementation.
|
||||||
|
|
||||||
|
Uses xAI's HTTP TTS endpoint documented at:
|
||||||
|
https://docs.x.ai/developers/model-capabilities/audio/text-to-speech
|
||||||
|
"""
|
||||||
|
|
||||||
|
from dataclasses import dataclass
|
||||||
|
from typing import AsyncGenerator, Optional
|
||||||
|
|
||||||
|
import aiohttp
|
||||||
|
from loguru import logger
|
||||||
|
|
||||||
|
from pipecat.frames.frames import ErrorFrame, Frame, TTSAudioRawFrame
|
||||||
|
from pipecat.services.settings import TTSSettings
|
||||||
|
from pipecat.services.tts_service import TTSService
|
||||||
|
from pipecat.transcriptions.language import Language, resolve_language
|
||||||
|
from pipecat.utils.tracing.service_decorators import traced_tts
|
||||||
|
|
||||||
|
|
||||||
|
def language_to_xai_language(language: Language) -> Optional[str]:
|
||||||
|
"""Convert a Language enum to xAI language code.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
language: The Language enum value to convert.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
The corresponding xAI language code, or None if not supported.
|
||||||
|
"""
|
||||||
|
LANGUAGE_MAP = {
|
||||||
|
Language.AR: "ar-EG",
|
||||||
|
Language.AR_EG: "ar-EG",
|
||||||
|
Language.AR_SA: "ar-SA",
|
||||||
|
Language.AR_AE: "ar-AE",
|
||||||
|
Language.BN: "bn",
|
||||||
|
Language.DE: "de",
|
||||||
|
Language.EN: "en",
|
||||||
|
Language.ES: "es-ES",
|
||||||
|
Language.ES_ES: "es-ES",
|
||||||
|
Language.ES_MX: "es-MX",
|
||||||
|
Language.FR: "fr",
|
||||||
|
Language.HI: "hi",
|
||||||
|
Language.ID: "id",
|
||||||
|
Language.IT: "it",
|
||||||
|
Language.JA: "ja",
|
||||||
|
Language.KO: "ko",
|
||||||
|
Language.PT: "pt-PT",
|
||||||
|
Language.PT_BR: "pt-BR",
|
||||||
|
Language.PT_PT: "pt-PT",
|
||||||
|
Language.RU: "ru",
|
||||||
|
Language.TR: "tr",
|
||||||
|
Language.VI: "vi",
|
||||||
|
Language.ZH: "zh",
|
||||||
|
}
|
||||||
|
|
||||||
|
return resolve_language(language, LANGUAGE_MAP, use_base_code=True)
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass
|
||||||
|
class XAITTSSettings(TTSSettings):
|
||||||
|
"""Settings for XAIHttpTTSService."""
|
||||||
|
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class XAIHttpTTSService(TTSService):
|
||||||
|
"""xAI HTTP text-to-speech service.
|
||||||
|
|
||||||
|
The service requests raw PCM audio so emitted ``TTSAudioRawFrame`` objects
|
||||||
|
match Pipecat's downstream expectations without extra decoding.
|
||||||
|
"""
|
||||||
|
|
||||||
|
Settings = XAITTSSettings
|
||||||
|
_settings: Settings
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
api_key: str,
|
||||||
|
base_url: str = "https://api.x.ai/v1/tts",
|
||||||
|
sample_rate: Optional[int] = None,
|
||||||
|
encoding: Optional[str] = "pcm",
|
||||||
|
aiohttp_session: Optional[aiohttp.ClientSession] = None,
|
||||||
|
settings: Optional[Settings] = None,
|
||||||
|
**kwargs,
|
||||||
|
):
|
||||||
|
"""Initialize the xAI TTS service.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
api_key: xAI API key for authentication.
|
||||||
|
base_url: xAI TTS endpoint. Defaults to ``https://api.x.ai/v1/tts``.
|
||||||
|
sample_rate: Audio sample rate. If None, uses default.
|
||||||
|
encoding: Output encoding format. Defaults to "pcm".
|
||||||
|
aiohttp_session: Optional shared aiohttp session.
|
||||||
|
settings: Runtime-updatable settings.
|
||||||
|
**kwargs: Additional keyword arguments passed to ``TTSService``.
|
||||||
|
"""
|
||||||
|
default_settings = self.Settings(
|
||||||
|
model=None,
|
||||||
|
voice="eve",
|
||||||
|
language=Language.EN,
|
||||||
|
)
|
||||||
|
|
||||||
|
if settings is not None:
|
||||||
|
default_settings.apply_update(settings)
|
||||||
|
|
||||||
|
super().__init__(
|
||||||
|
sample_rate=sample_rate,
|
||||||
|
push_start_frame=True,
|
||||||
|
push_stop_frames=True,
|
||||||
|
settings=default_settings,
|
||||||
|
**kwargs,
|
||||||
|
)
|
||||||
|
|
||||||
|
self._api_key = api_key
|
||||||
|
self._base_url = base_url
|
||||||
|
self._session = aiohttp_session
|
||||||
|
self._session_owner = aiohttp_session is None
|
||||||
|
self._encoding = encoding
|
||||||
|
|
||||||
|
def can_generate_metrics(self) -> bool:
|
||||||
|
"""Check if this service can generate processing metrics."""
|
||||||
|
return True
|
||||||
|
|
||||||
|
def language_to_service_language(self, language: Language) -> Optional[str]:
|
||||||
|
"""Convert a Language enum to xAI language format.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
language: The language to convert.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
The xAI-specific language code, or None if not supported.
|
||||||
|
"""
|
||||||
|
return language_to_xai_language(language)
|
||||||
|
|
||||||
|
async def start(self, frame):
|
||||||
|
"""Start the xAI TTS service."""
|
||||||
|
await super().start(frame)
|
||||||
|
if self._session is None or self._session.closed:
|
||||||
|
self._session = aiohttp.ClientSession()
|
||||||
|
self._session_owner = True
|
||||||
|
|
||||||
|
async def stop(self, frame):
|
||||||
|
"""Stop the xAI TTS service."""
|
||||||
|
await super().stop(frame)
|
||||||
|
await self._close_session()
|
||||||
|
|
||||||
|
async def cancel(self, frame):
|
||||||
|
"""Cancel the xAI TTS service."""
|
||||||
|
await super().cancel(frame)
|
||||||
|
await self._close_session()
|
||||||
|
|
||||||
|
async def _close_session(self):
|
||||||
|
if self._session_owner and self._session and not self._session.closed:
|
||||||
|
await self._session.close()
|
||||||
|
if self._session_owner:
|
||||||
|
self._session = None
|
||||||
|
|
||||||
|
@traced_tts
|
||||||
|
async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:
|
||||||
|
"""Generate speech from text using xAI's TTS API."""
|
||||||
|
logger.debug(f"{self}: Generating TTS [{text}]")
|
||||||
|
|
||||||
|
if self._session is None or self._session.closed:
|
||||||
|
self._session = aiohttp.ClientSession()
|
||||||
|
self._session_owner = True
|
||||||
|
|
||||||
|
payload = {
|
||||||
|
"text": text,
|
||||||
|
"voice_id": self._settings.voice,
|
||||||
|
"output_format": {
|
||||||
|
"codec": self._encoding,
|
||||||
|
"sample_rate": self.sample_rate,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
if self._settings.language:
|
||||||
|
payload["language"] = str(self._settings.language)
|
||||||
|
|
||||||
|
headers = {
|
||||||
|
"Authorization": f"Bearer {self._api_key}",
|
||||||
|
"Content-Type": "application/json",
|
||||||
|
}
|
||||||
|
|
||||||
|
measuring_ttfb = True
|
||||||
|
try:
|
||||||
|
async with self._session.post(
|
||||||
|
self._base_url, json=payload, headers=headers
|
||||||
|
) as response:
|
||||||
|
if response.status != 200:
|
||||||
|
error = await response.text(errors="ignore")
|
||||||
|
yield ErrorFrame(
|
||||||
|
error=f"Error getting audio (status: {response.status}, error: {error})"
|
||||||
|
)
|
||||||
|
return
|
||||||
|
|
||||||
|
await self.start_tts_usage_metrics(text)
|
||||||
|
|
||||||
|
async for chunk in response.content.iter_chunked(self.chunk_size):
|
||||||
|
if not chunk:
|
||||||
|
continue
|
||||||
|
if measuring_ttfb:
|
||||||
|
await self.stop_ttfb_metrics()
|
||||||
|
measuring_ttfb = False
|
||||||
|
yield TTSAudioRawFrame(
|
||||||
|
chunk,
|
||||||
|
self.sample_rate,
|
||||||
|
1,
|
||||||
|
context_id=context_id,
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
yield ErrorFrame(error=f"Unknown error occurred: {e}")
|
||||||
91
tests/test_xai_tts.py
Normal file
91
tests/test_xai_tts.py
Normal file
@@ -0,0 +1,91 @@
|
|||||||
|
#
|
||||||
|
# Copyright (c) 2024-2026, Daily
|
||||||
|
#
|
||||||
|
# SPDX-License-Identifier: BSD 2-Clause License
|
||||||
|
#
|
||||||
|
|
||||||
|
"""Tests for XAIHttpTTSService."""
|
||||||
|
|
||||||
|
import asyncio
|
||||||
|
import unittest
|
||||||
|
|
||||||
|
import aiohttp
|
||||||
|
import pytest
|
||||||
|
from aiohttp import web
|
||||||
|
|
||||||
|
from pipecat.frames.frames import (
|
||||||
|
AggregatedTextFrame,
|
||||||
|
TTSAudioRawFrame,
|
||||||
|
TTSSpeakFrame,
|
||||||
|
TTSStartedFrame,
|
||||||
|
TTSStoppedFrame,
|
||||||
|
TTSTextFrame,
|
||||||
|
)
|
||||||
|
from pipecat.services.xai.tts import XAIHttpTTSService
|
||||||
|
from pipecat.tests.utils import run_test
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_run_xai_tts_success(aiohttp_client):
|
||||||
|
"""xAI TTS should send the documented request body and emit PCM frames."""
|
||||||
|
|
||||||
|
request_bodies = []
|
||||||
|
|
||||||
|
async def handler(request):
|
||||||
|
request_bodies.append(await request.json())
|
||||||
|
|
||||||
|
response = web.StreamResponse(
|
||||||
|
status=200,
|
||||||
|
reason="OK",
|
||||||
|
headers={"Content-Type": "audio/pcm"},
|
||||||
|
)
|
||||||
|
await response.prepare(request)
|
||||||
|
await response.write(b"\x00\x01\x02\x03" * 1024)
|
||||||
|
await asyncio.sleep(0.01)
|
||||||
|
await response.write(b"\x04\x05\x06\x07" * 1024)
|
||||||
|
await response.write_eof()
|
||||||
|
return response
|
||||||
|
|
||||||
|
app = web.Application()
|
||||||
|
app.router.add_post("/v1/tts", handler)
|
||||||
|
client = await aiohttp_client(app)
|
||||||
|
base_url = str(client.make_url("/v1/tts"))
|
||||||
|
|
||||||
|
async with aiohttp.ClientSession() as session:
|
||||||
|
tts_service = XAIHttpTTSService(
|
||||||
|
api_key="test-key",
|
||||||
|
base_url=base_url,
|
||||||
|
aiohttp_session=session,
|
||||||
|
sample_rate=24000,
|
||||||
|
)
|
||||||
|
|
||||||
|
down_frames, _ = await run_test(
|
||||||
|
tts_service,
|
||||||
|
frames_to_send=[TTSSpeakFrame(text="Hello from xAI.")],
|
||||||
|
)
|
||||||
|
|
||||||
|
frame_types = [type(frame) for frame in down_frames]
|
||||||
|
assert AggregatedTextFrame in frame_types
|
||||||
|
assert TTSStartedFrame in frame_types
|
||||||
|
assert TTSStoppedFrame in frame_types
|
||||||
|
assert TTSTextFrame in frame_types
|
||||||
|
|
||||||
|
audio_frames = [frame for frame in down_frames if isinstance(frame, TTSAudioRawFrame)]
|
||||||
|
assert audio_frames
|
||||||
|
assert all(frame.sample_rate == 24000 for frame in audio_frames)
|
||||||
|
assert all(frame.num_channels == 1 for frame in audio_frames)
|
||||||
|
|
||||||
|
assert len(request_bodies) == 1
|
||||||
|
assert request_bodies[0] == {
|
||||||
|
"text": "Hello from xAI.",
|
||||||
|
"voice_id": "eve",
|
||||||
|
"language": "en",
|
||||||
|
"output_format": {
|
||||||
|
"codec": "pcm",
|
||||||
|
"sample_rate": 24000,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
unittest.main()
|
||||||
2
uv.lock
generated
2
uv.lock
generated
@@ -4966,7 +4966,7 @@ requires-dist = [
|
|||||||
{ name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1,<1" },
|
{ name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1,<1" },
|
||||||
{ name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" },
|
{ 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", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "smallest", "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", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "smallest", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper", "xai"]
|
||||||
|
|
||||||
[package.metadata.requires-dev]
|
[package.metadata.requires-dev]
|
||||||
dev = [
|
dev = [
|
||||||
|
|||||||
Reference in New Issue
Block a user