Help for using Voxabot SSML Editor

Basic usage of Voxabot SSML Editor

  1. Paste the text that you want to convert to audio

  2. Chose the Text-to-Speech Engine that you want to use on the TTS Engine tab

  3. Chose the language in which the text is written on the Languages tab

  4. Chose the voice you want to use on the Voices tab

  5. Click on Convert To Audio

  6. Click on Play to listen to the generated audio

  7. Save the audio file generated by clicking on (Save Audio)

Customizing the audio output using SSML

The Editor page is splitted in two panes. In the left pane you can paste the text that you want to convert to audio and in the right pane you can see the same text with all the SSML code embedded.

If you are not happy with the default audio output, you can modify it by inserting all standard SSML tags (break, emphasis, language, pitch, rate, volume, phoneme, say-as, alias, sentence) in the left pane without having to write any SSML tags manually. In the left pane you will see a visual representation of the SSML tags and in the right pane you will see the resulting SSML code. You can experiment by changing the SSML code and generating new audio output until you are satisfied with the result.

Saving text with embedded SSML code

If you want to save your text with embedded SSML code to work with it later or to use it somewhere else, you can do so by clicking on the Export SSML tab. This will create a file with an SSML extension.

Explanation of all tabs in Voxabot SSML Editor

Custom

Some of the new synthetic voices can produce effects not included in the standard SSML tag set. Non standard SSML tabs can be entered using the Custom tab. You can find more information about custom SSML tags supported for each TTS engine in the following links:

Amazon Polly : https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html

Microsoft Azure Speech : https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-synthesis-markup?tabs=csharp#adjust-speaking-styles

Google GCP Cloud : https://cloud.google.com/text-to-speech/docs/ssml

Tools

The Tools tab includes two options:

  1. SSML code, which opens a box where advanced users can write the SSML code directly.

  2. Wordcount, which opens a window showing complete word count details.

Import SSML

This option opens a window where you can paste any text which already contains SSML code. After you paste the text and press OK, the text will be imported into the Editor. This is useful when you already have some text with embedded SSML code that you want to work with.

Export SSML

This option lets you export the text into a file with the extension SSML which you can save in your hard disk.

TTS Engine

Here you select the TTS engine that you want to use: Amazon, Google or Microsoft

Languages

Here you select the language in which the text is written. The TTS engine needs to know the language in which the text is written in order to render it correctly in that language.

Voices

Select the voice that you want to use from the different voices available from each TTS engine. For a list of voices offered by each TTS engine, see below:

Amazon Polly : Currently Amazon Polly provides approximately 15 neural voices and about 60 standard voices in almost 30 languages: https://docs.aws.amazon.com/polly/latest/dg/voicelist.html

Microsoft Azure : Microsoft provides around 70 neural voices and even a higher number of standard voices in about 50 languages: https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support#text-to-speech

Google : Google provides around 250 voices using standard and Wavenet technology in about 40 languages: https://cloud.google.com/text-to-speech/docs/voices

copyright 2023 Voxabot LLC