当前位置:网站首页>Microsoft speech synthesis assistant v1.3 text to speech tool, real speech AI generator

Microsoft speech synthesis assistant v1.3 text to speech tool, real speech AI generator

2022-07-06 02:34:00 By long

Preface

Microsoft speech synthesis assistant uses powerful Microsoft AI Speech database , Synthesize unique reading audio close to human voice .

Have 20 Many dubbing staff , Use expressive and human like sounds , Bring programs such as text readers and voice enabled assistants to life .

Neural network text to speech support a variety of Reading Styles , Including news broadcast 、 Customer service 、 Shout 、 Whisper and be happy 、 Sadness and other emotions .

Microsoft speech synthesis assistant

by:bill3k

software function : Import TXT file , Import SRT Subtitle files , Save export edits , Support pause , Custom pause time , audition , Partial audition , translate , Partial translation , Automatic typesetting , Automatic punctuation , Text substitution , Sensitive words remind , Sensitive word substitution ,SSML Multi person voice mixing and other functions .
 Insert picture description here

New characteristics

1、 newly added Edge Dubbing interface

2、 New software setting interface , It is convenient to switch various functions of the software and switch interfaces ( The setting interface is in the icon right-click menu in the lower right corner of the taskbar )

3、 Remove the word limit , Adopt the method of segmented downloading and merging 2500 Word limit problem

4、 New subtitle function , Save the audio and generate it in the audio directory SRT Subtitle files ( Subtitles often calculate the occupation time of single words according to the number of words and audio , At the default speaking speed 、 tone , The volume ,EDGE Interface , The accuracy is very high without pause , This function is enabled in the setting interface )

5、 Batch conversion adds the function of playing while compositing , When you click batch synthesis, you will be prompted whether to turn on the playback function .

6、 New user-defined screenshot shortcut key function .

7、 Optimize software startup speed and so on .

notes :Edge The interface only supports text to audio , I won't support it SSML. Less than 300 Word slightly faster than free interface .

Instructions

link :https://u9baoku.xyz/6735.html

I won't support it Win7,SSML For the use of speech synthesis markers, please refer to

https://docs.microsoft.com/zh-cn/azure/cognitive-services/speech-service/speech-synthesis-markup

Recommend another web version

https://toolb.cn/textspeech

原网站

版权声明
本文为[By long]所创,转载请带上原文链接,感谢
https://yzsam.com/2022/187/202207060231096180.html