如何将文本发送到文本转语音 [英] How to send a lexicon to text-to-speech
问题描述
我想帮助将新词典合并到文字转语音API中。
I'd like help with incorporating a new lexicon into the Text-to-Speech API.
I已经成功发送了文本,并获得了有效的mp3文件。现在我正在尝试合并一个带有困难发音的词典。
I've successfully sent text and have gotten mp3 files that work. Now I'm trying to incorporate a lexicon with difficult pronunciations.
我正在使用Python SDK进行文字转语音,并且文档中几乎没有问题。
I'm using the Python SDK for Text-to-Speech and have few questions from the documentation.
- 这个引用'lexicon Element SSML(Microsoft.Speech)'是否已过时?
- Is this reference 'lexicon Element SSML (Microsoft.Speech)' outdated?
- 我使用什么URI?
- What URI do I use?
- 当我使用本文档中的说明时,我收到以下错误消息: 状态代码:400。 某物
出错了。检查您的订阅密钥和标题。我该如何解决或调查?
- 词典必须采用什么格式?我在文档中看到了一个以.pls格式引用词典的示例。我该如何创建呢?以下是参考资料:
- What format does the lexicon have to be in? I saw an example in the document that referenced a lexicon in a .pls format. How do I create this? Here is the reference:
<?xml version =" 1.0"?>
< 说话
版本 = " 1.0"
xmlns = " http://www.w3.org/2001/10/synthesis"
xml:lang = " en-US" >
< lexicon
uri = " c:\ Test \whatchamacallit.pls"
type = " application / pls + xml" />
Gimme the whatmamacallit。 < / 发言>
<?xml version="1.0"?> <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US"> <lexicon uri="c:\Test\whatchamacallit.pls" type="application/pls+xml"/> Gimme the whatchamacallit. </speak>
谢谢!
< style type =" text / css"> p.p1 {margin:0.0px 0.0px 0.0px 0.0px; font:11.0px Menlo; color:#000000 } span.s1 {font-variant-ligatures:no-common-ligatures}< / style>
<style type="text/css">p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 11.0px Menlo; color: #000000} span.s1 {font-variant-ligatures: no-common-ligatures} </style>
推荐答案
你好,
这是
链接?此内容未定期更新,因此可能不是最新内容。
Is this the link that you are referring to? This content is not updated regularly so it might not be current.
我认为您应该看看这个有关文字的自定义发音的
页面演讲。
I think you should look at this page for custom pronunciations with text to speech.
-Rohit
这篇关于如何将文本发送到文本转语音的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!