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

Revert aligning voice_id name in TTS service constructor

Browse Source
This commit is contained in:
Mark Backman
2024-10-02 11:07:48 -04:00
parent d75a02dc51
commit 3d642df2b0
8 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/foundational/07c-interruptible-deepgram.py
View File

@@ -50,7 +50,7 @@ async def main():
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice_id="aura-helios-en") tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o") llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

2
examples/foundational/07e-interruptible-playht.py
View File

@@ -52,7 +52,7 @@ async def main():
tts = PlayHTTTSService( tts = PlayHTTTSService(
user_id=os.getenv("PLAYHT_USER_ID"), user_id=os.getenv("PLAYHT_USER_ID"),
api_key=os.getenv("PLAYHT_API_KEY"), api_key=os.getenv("PLAYHT_API_KEY"),
voice_id="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json", voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
) )
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o") llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

2
examples/foundational/07g-interruptible-openai-tts.py
View File

@@ -48,7 +48,7 @@ async def main():
), ),
) )
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice_id="alloy") tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="alloy")
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o") llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

2
examples/foundational/16-gpu-container-local-bot.py
View File

@@ -55,7 +55,7 @@ async def main():
tts = DeepgramTTSService( tts = DeepgramTTSService(
aiohttp_session=session, aiohttp_session=session,
api_key=os.getenv("DEEPGRAM_API_KEY"), api_key=os.getenv("DEEPGRAM_API_KEY"),
voice_id="aura-asteria-en", voice="aura-asteria-en",
base_url="http://0.0.0.0:8080/v1/speak", base_url="http://0.0.0.0:8080/v1/speak",
) )

4
src/pipecat/services/azure.py
View File

@@ -178,7 +178,7 @@ class AzureTTSService(TTSService):
*, *,
api_key: str, api_key: str,
region: str, region: str,
voice_id="en-US-SaraNeural", voice="en-US-SaraNeural",
sample_rate: int = 16000, sample_rate: int = 16000,
params: InputParams = InputParams(), params: InputParams = InputParams(),
**kwargs, **kwargs,
@@ -200,7 +200,7 @@ class AzureTTSService(TTSService):
"volume": params.volume, "volume": params.volume,
} }
self.set_voice(voice_id) self.set_voice(voice)
def can_generate_metrics(self) -> bool: def can_generate_metrics(self) -> bool:
return True return True

4
src/pipecat/services/deepgram.py
View File

@@ -49,7 +49,7 @@ class DeepgramTTSService(TTSService):
self, self,
*, *,
api_key: str, api_key: str,
voice_id: str = "aura-helios-en", voice: str = "aura-helios-en",
sample_rate: int = 16000, sample_rate: int = 16000,
encoding: str = "linear16", encoding: str = "linear16",
**kwargs, **kwargs,
@@ -60,7 +60,7 @@ class DeepgramTTSService(TTSService):
"sample_rate": sample_rate, "sample_rate": sample_rate,
"encoding": encoding, "encoding": encoding,
} }
self.set_voice(voice_id) self.set_voice(voice)
self._deepgram_client = DeepgramClient(api_key=api_key) self._deepgram_client = DeepgramClient(api_key=api_key)
def can_generate_metrics(self) -> bool: def can_generate_metrics(self) -> bool:

4
src/pipecat/services/openai.py
View File

@@ -381,7 +381,7 @@ class OpenAITTSService(TTSService):
self, self,
*, *,
api_key: str | None = None, api_key: str | None = None,
voice_id: str = "alloy", voice: str = "alloy",
model: Literal["tts-1", "tts-1-hd"] = "tts-1", model: Literal["tts-1", "tts-1-hd"] = "tts-1",
sample_rate: int = 24000, sample_rate: int = 24000,
**kwargs, **kwargs,
@@ -392,7 +392,7 @@ class OpenAITTSService(TTSService):
"sample_rate": sample_rate, "sample_rate": sample_rate,
} }
self.set_model_name(model) self.set_model_name(model)
self.set_voice(voice_id) self.set_voice(voice)
self._client = AsyncOpenAI(api_key=api_key) self._client = AsyncOpenAI(api_key=api_key)

4
src/pipecat/services/playht.py
View File

@@ -32,7 +32,7 @@ except ModuleNotFoundError as e:
class PlayHTTTSService(TTSService): class PlayHTTTSService(TTSService):
def __init__( def __init__(
self, *, api_key: str, user_id: str, voice_id: str, sample_rate: int = 16000, **kwargs self, *, api_key: str, user_id: str, voice_url: str, sample_rate: int = 16000, **kwargs
): ):
super().__init__(sample_rate=sample_rate, **kwargs) super().__init__(sample_rate=sample_rate, **kwargs)
@@ -49,7 +49,7 @@ class PlayHTTTSService(TTSService):
"format": Format.FORMAT_WAV, "format": Format.FORMAT_WAV,
"voice_engine": "PlayHT2.0-turbo", "voice_engine": "PlayHT2.0-turbo",
} }
self.set_voice(voice_id) self.set_voice(voice_url)
self._options = TTSOptions( self._options = TTSOptions(
voice=self._voice_id, voice=self._voice_id,
sample_rate=self._settings["sample_rate"], sample_rate=self._settings["sample_rate"],