Support 180+ voices across 30+ languages and variants, such as Arabic, Czech (Czech Republic), Danish (Denmark), Dutch (Netherlands), English (Australia), English (India), English (UK), English (US), Filipino (Philippines), Finnish (Finland), French (Canada), French (France), German (Germany), Greek (Greece), Hindi (India), Hungarian (Hungary), Indonesian (Indonesia), Italian (Italy), Japanese (Japan), Korean (South Korea), Mandarin Chinese, Norwegian (Norway), Polish (Poland), Portuguese (Brazil), Portuguese (Portugal), Russian (Russia), Slovak (Slovakia), Spanish (Spain), Swedish (Sweden), Turkish (Turkey), Ukrainian (Ukraine), Vietnamese (Vietnam).
DeepMind has done groundbreaking research in machine learning models to generate speech that mimics human voices and sounds more natural, reducing the gap with human performance by 70%. Cloud Text-to-Speech offers exclusive access to 90+ WaveNet voices and will continue to add more over time.
The Standard price is lower and the quality is good enough, but the WaveNet quality is much better. and some language has no WaveNet voice type and vice versa. You make decisions by your self.
In my opinion, if you want to learn SSMML or think the Standard quality is good for you, you can choose Standard voice type. If you want to much better quality, you can choose WaveNet voice type.
|Serial numbers||Language||Sex||Voice type||Voice name|
|8||Czech (Czech Republic)||Female||Wavenet||cs-CZ-Wavenet-A|
|59||Korean (South Korea)||Female||Wavenet||ko-KR-Wavenet-B|
|60||Korean (South Korea)||Male||Wavenet||ko-KR-Wavenet-C|
|61||Korean (South Korea)||Male||Wavenet||ko-KR-Wavenet-D|
|62||Korean (South Korea)||Female||Wavenet||ko-KR-Wavenet-A|
|116||Korean (South Korea)||Female||Standard||ko-KR-Standard-A|
|117||Korean (South Korea)||Female||Standard||ko-KR-Standard-B|
|118||Korean (South Korea)||Male||Standard||ko-KR-Standard-C|
|119||Korean (South Korea)||Male||Standard||ko-KR-Standard-D|
|137||Czech (Czech Republic)||Female||Standard||cs-CZ-Standard-A|
You can setup Language, Voice type, SEX, Speaking Rate, Pitch, Volume, and Audio Profiles.
Speech Synthesis Markup Language (SSML) is an XML-based markup language for speech synthesis applications. It is a recommendation of the W3C's voice browser working group. SSML is often embedded in VoiceXML scripts to drive interactive telephony systems. However, it also may be used alone, such as for creating audio books. For desktop applications, other markup languages are popular, including Apple's embedded speech commands, and Microsoft's SAPI Text to speech (TTS) markup, also an XML language. It is also used when writing third-party skills for Google Assistant or Amazon Alexa. To learn more about the speak element, see the W3 specification.
Note that not all of the elements and options described in the W3 SSML specification are currently supported by Text-to-Speech. You can visit Google document Speech Synthesis Markup Language (SSML) to get more details
Google SSML supports <speck>, <break>, <say-as>, <audio> <p>, <s>, <sub>, <mark>, <prosody>, <emphasis>, <par>, <seq>, <media>.
VaySoft Text to Speech Converter for Google supports almost all or them.
In theory, 5000 characters are upper limit value, if exceed 5000 characters, you will get error result, but the points in your account will still cost.
in our experience, too many characters will have a bad result, especially with SSML mode. Google is continuous improvement on it. you can try.
If the voice type is standard, one character in text/SSML one point will cost. if the voice is WaveNet, one character in text/SSML three points will cost.
For example you want to convert "This is a book." to sound file. the amount of characters is 15. If the voice type is standard, 15 points will cost, if the voice type is WaveNet, 45 points will cost.
Note: The number of characters will be equal to or less than the number of bytes represented by the text. This includes alphanumeric characters, punctuation, and white spaces. Some character sets use more than one byte for a character. For example, Japanese (ja-JP) characters in UTF-8 typically require more than one byte each. In this case, you are only charged for one character, not multiple bytes.
Our desktop tool will try to find if errors exist in your text content before submitting your request to our web server, if found, you will get error messages, and the points will not cost.
But, we cannot guarantee to find all errors. if the request submits to our server, no matter the result is correct or has errors, the points will cost.
In normal cases, the errors will happen if your network is Unstable， I recommend, you make sure the network is normal.
Our system identifies your account base on your email account and password. So, please use your frequently used mailbox when you sign up for our system. and make sure your mailbox can receive our email from vaysoft. The email account needs not to be the same as your PayPal email account. You can use one PayPal account to make payment for multiple signs in email accounts.
Only one PC can run my converter, you can not sign in your system on multiple PC in the meantime.
If you sign in at one PC and sign in at another PC, you cannot use our product in the previous PC, you have to sign in again.
We only accept PayPal by far. PayPal support many payment ways and make your payment safe. Maybe we will provide more types someday.
You can make payment in the VaySoft Text to Speech Converter for Google tool. whenever you want to buy points, you can click the "buy points online" button, then select a plan item in buy points windows, make payment using PayPal online. After your payment, you will get the points in five minutes.
Please see the details.
We have a strict no-refund policy for all of our products. Once you make payment, you cannot request a money refund.
Please try our product well before you buy it.
You can use one PayPal account to make payment for multiple email accounts.
If you have a valid account and have points, you can use all features of the converter tool, otherwise, you cannot save or copy/past the content of Text/SSML, and you cannot convert the content of Text/SSML to voice sound file.
We do not save you text content and do not save the output voice sound file too.
We directly submit your text content to google and get back the voice sound file to you.
You cannot use the sound file for illegal purposes.
We do not save the output voice sound file, you have to keep your sound file by your self. if you lost it, you can to convert again.
We will not pass any details of you to third parties or persons.
We will send very important information to your email account, but not often. If you want to know any latest information, please visit my website often.
In normal case, our normal service is enough for you, the average combined cost is very low. You do not need to fire one or two IT programmers to develop a project and maintain it days by days to make sure it works properly.
IIf you have a very large text convert to speech, it is necessary to build your system. We provide this service. please contact us.
If you have any suggestions of the features adding, please contact us. Some request is free, the other maybe need some fee.