wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Review comments by aconchillo.

Browse Source
This commit is contained in:
Adnan Siddiquei
2025-03-14 10:52:13 +00:00
parent 1bf964a667
commit 7dec8431e1
2 changed files with 4 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@@ -45,7 +45,7 @@ aws = [ "boto3~=1.35.99" ]
azure = [ "azure-cognitiveservices-speech~=1.42.0"] azure = [ "azure-cognitiveservices-speech~=1.42.0"]
canonical = [ "aiofiles~=24.1.0" ] canonical = [ "aiofiles~=24.1.0" ]
cartesia = [ "cartesia~=1.3.1", "websockets~=13.1" ] cartesia = [ "cartesia~=1.3.1", "websockets~=13.1" ]
neuphonic = [ "pyneuphonic~=1.5.11", "websockets~=13.1" ] neuphonic = [ "pyneuphonic~=1.5.12", "websockets~=13.1" ]
cerebras = [] cerebras = []
deepseek = [] deepseek = []
daily = [ "daily-python~=0.15.0" ] daily = [ "daily-python~=0.15.0" ]

9
src/pipecat/services/neuphonic.py
View File

@@ -27,8 +27,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame, TTSStoppedFrame,
) )
from pipecat.processors.frame_processor import FrameDirection from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import TTSService, WordTTSService from pipecat.services.ai_services import InterruptibleTTSService, TTSService
from pipecat.services.websocket_service import WebsocketService
from pipecat.transcriptions.language import Language from pipecat.transcriptions.language import Language
# See .env.example for Neuphonic configuration needed # See .env.example for Neuphonic configuration needed
@@ -71,7 +70,7 @@ def language_to_neuphonic_lang_code(language: Language) -> Optional[str]:
return result return result
class NeuphonicTTSService(WordTTSService, WebsocketService): class NeuphonicTTSService(InterruptibleTTSService):
class InputParams(BaseModel): class InputParams(BaseModel):
language: Optional[Language] = Language.EN language: Optional[Language] = Language.EN
speed: Optional[float] = 1.0 speed: Optional[float] = 1.0
@@ -88,7 +87,7 @@ class NeuphonicTTSService(WordTTSService, WebsocketService):
params: InputParams = InputParams(), params: InputParams = InputParams(),
**kwargs, **kwargs,
): ):
WordTTSService.__init__( super().__init__(
self, self,
aggregate_sentences=True, aggregate_sentences=True,
push_text_frames=False, push_text_frames=False,
@@ -97,7 +96,6 @@ class NeuphonicTTSService(WordTTSService, WebsocketService):
sample_rate=sample_rate, sample_rate=sample_rate,
**kwargs, **kwargs,
) )
WebsocketService.__init__(self)
self._api_key = api_key self._api_key = api_key
self._url = url self._url = url
@@ -232,7 +230,6 @@ class NeuphonicTTSService(WordTTSService, WebsocketService):
msg = json.loads(message) msg = json.loads(message)
if msg.get("data", {}).get("audio") is not None: if msg.get("data", {}).get("audio") is not None:
await self.stop_ttfb_metrics() await self.stop_ttfb_metrics()
self.start_word_timestamps()
audio = base64.b64decode(msg["data"]["audio"]) audio = base64.b64decode(msg["data"]["audio"])
frame = TTSAudioRawFrame(audio, self.sample_rate, 1) frame = TTSAudioRawFrame(audio, self.sample_rate, 1)