Microsoft Azure text to Speech 如何不说话直接保存文件?
How Microsoft Azure text to Speech without speaking just save file directly?
import azure.cognitiveservices.speech as speechsdk
speech_key="speech key"
service_region="eastus"
def speech_synthesis_with_auto_language_detection_to_speaker(text):
"""performs speech synthesis to the default speaker with auto language detection
Note: this is a preview feature, which might be updated in future versions."""
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
# create the auto detection language configuration without specific languages
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig()
# Creates a speech synthesizer using the default speaker as audio output.
speech_synthesizer = speechsdk.SpeechSynthesizer(
speech_config=speech_config, auto_detect_source_language_config=auto_detect_source_language_config)
result = speech_synthesizer.speak_text_async(text).get()
# Check result
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
print("Speech synthesized to speaker for text [{}]".format(text))
stream = speechsdk.AudioDataStream(result)
stream.save_to_wav_file(r"C:\Users\user\Desktop\outputfff.wav")
speech_synthesis_with_auto_language_detection_to_speaker("तू कसा आहेस ")
如何不说话直接保存文件到wave请帮忙
好像你可以看到 azure 认知服务的文档,他们没有添加关于如何只保存 speech_synthesizer calss 也没有任何方法只保存文件而不播放它
试试这个:
import azure.cognitiveservices.speech as speechsdk
speech_key=""
service_region=""
def speech_synthesis_with_auto_language_detection_to_speaker(text):
"""performs speech synthesis to the default speaker with auto language detection
Note: this is a preview feature, which might be updated in future versions."""
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
# create the auto detection language configuration without specific languages
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig()
# Creates a speech synthesizer using the default speaker as audio output.
speech_synthesizer = speechsdk.SpeechSynthesizer(
speech_config=speech_config, auto_detect_source_language_config=auto_detect_source_language_config,audio_config=None)
result = speech_synthesizer.speak_text_async(text).get();
# Check result
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
print("Speech synthesized to speaker for text [{}]".format(text))
stream = speechsdk.AudioDataStream(result)
stream.save_to_wav_file(r"C:\Users\user\Desktop\outputfff.wav")
speech_synthesis_with_auto_language_detection_to_speaker("तू कसा आहेस ")
只需为 speechsdk.SpeechSynthesizer
指定 audio_config=None
。
import azure.cognitiveservices.speech as speechsdk
speech_key="speech key"
service_region="eastus"
def speech_synthesis_with_auto_language_detection_to_speaker(text):
"""performs speech synthesis to the default speaker with auto language detection
Note: this is a preview feature, which might be updated in future versions."""
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
# create the auto detection language configuration without specific languages
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig()
# Creates a speech synthesizer using the default speaker as audio output.
speech_synthesizer = speechsdk.SpeechSynthesizer(
speech_config=speech_config, auto_detect_source_language_config=auto_detect_source_language_config)
result = speech_synthesizer.speak_text_async(text).get()
# Check result
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
print("Speech synthesized to speaker for text [{}]".format(text))
stream = speechsdk.AudioDataStream(result)
stream.save_to_wav_file(r"C:\Users\user\Desktop\outputfff.wav")
speech_synthesis_with_auto_language_detection_to_speaker("तू कसा आहेस ")
如何不说话直接保存文件到wave请帮忙
好像你可以看到 azure 认知服务的文档,他们没有添加关于如何只保存 speech_synthesizer calss 也没有任何方法只保存文件而不播放它
试试这个:
import azure.cognitiveservices.speech as speechsdk
speech_key=""
service_region=""
def speech_synthesis_with_auto_language_detection_to_speaker(text):
"""performs speech synthesis to the default speaker with auto language detection
Note: this is a preview feature, which might be updated in future versions."""
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
# create the auto detection language configuration without specific languages
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig()
# Creates a speech synthesizer using the default speaker as audio output.
speech_synthesizer = speechsdk.SpeechSynthesizer(
speech_config=speech_config, auto_detect_source_language_config=auto_detect_source_language_config,audio_config=None)
result = speech_synthesizer.speak_text_async(text).get();
# Check result
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
print("Speech synthesized to speaker for text [{}]".format(text))
stream = speechsdk.AudioDataStream(result)
stream.save_to_wav_file(r"C:\Users\user\Desktop\outputfff.wav")
speech_synthesis_with_auto_language_detection_to_speaker("तू कसा आहेस ")
只需为 speechsdk.SpeechSynthesizer
指定 audio_config=None
。