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

Initialize the speech_recognition_language for Azure TTS

Browse Source
This commit is contained in:
Mark Backman
2024-11-07 15:14:05 -05:00
parent 29925a8f21
commit aefe190c9f
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/pipecat/services/azure.py
View File

@@ -43,8 +43,8 @@ try:
ResultReason, ResultReason,
SpeechConfig, SpeechConfig,
SpeechRecognizer, SpeechRecognizer,
SpeechSynthesizer,
SpeechSynthesisOutputFormat, SpeechSynthesisOutputFormat,
SpeechSynthesizer,
) )
from azure.cognitiveservices.speech.audio import ( from azure.cognitiveservices.speech.audio import (
AudioStreamFormat, AudioStreamFormat,
@@ -128,11 +128,6 @@ class AzureTTSService(TTSService):
): ):
super().__init__(sample_rate=sample_rate, **kwargs) super().__init__(sample_rate=sample_rate, **kwargs)
speech_config = SpeechConfig(subscription=api_key, region=region)
speech_config.set_speech_synthesis_output_format(sample_rate_to_output_format(sample_rate))
self._speech_synthesizer = SpeechSynthesizer(speech_config=speech_config, audio_config=None)
self._settings = { self._settings = {
"sample_rate": sample_rate, "sample_rate": sample_rate,
"emphasis": params.emphasis, "emphasis": params.emphasis,
@@ -147,6 +142,15 @@ class AzureTTSService(TTSService):
"volume": params.volume, "volume": params.volume,
} }
speech_config = SpeechConfig(
subscription=api_key,
region=region,
speech_recognition_language=self._settings["language"],
)
speech_config.set_speech_synthesis_output_format(sample_rate_to_output_format(sample_rate))
self._speech_synthesizer = SpeechSynthesizer(speech_config=speech_config, audio_config=None)
self.set_voice(voice) self.set_voice(voice)
def can_generate_metrics(self) -> bool: def can_generate_metrics(self) -> bool: