App.Voxabat editor is a plain text editor. You can edit,copy and paste text.
In your Text-to-Speech request you can add somecustomization in the audio response by providing SSML tags. App.Voxabot letsyou add easily all the standard SSML tags (break, emphasis, language, pitch,rate, volume, phoneme, say-as, alias, sentence).
With the development of neural voices, each TTS provider isintroducing advanced custom SSML tags. These custom tags can be entered usingthe Customtab in the editor. You can find more information about custom SSML tagssupported for each TTS connector in the following links:
Microsoft Azure Speech
Google GCP Cloud
Options included in the Tool tab:
<>SSML code: This option opens a boxwhere advanced users can write the SSML code directly.
Wordcount: It opens a window showing completewordcount details.
Import SSML: This option lets you import text containingSSML code into the App.Voxabot editor. Click Tools>Import SSML andpaste the SSML text that you want to import into the editor.
Export SSML: This option lets you export alltext displayed in the editor into a file with the extension SSML which you cansave in your hard disk.
Use this button to download the generated audio file
Use this button to delete selected SSML code
Undo button. It erases the last change done to thedocument, reverting it to a previous state. Same as Ctrl+Z
Redo button. The redo button restores any actions that werepreviously undone using an undo. Same as Ctrl+Y
To generate text to speech, App.Voxabot needs to beconnected to a TTS engine. The first time you sign in with Google, App.Voxabotprovides connections with the following TTS engines:
● AWS Polly TTS (Amazon)
● GCP Cloud TTS (Google)
● Azure Speech TTS(Microsoft)
Tabs Languages and Voices let you select theavailable languages and corresponding voices for each TTS engine.
Currently App.Voxabot offers connections to the voicesavailable from Amazon, Microsoft and Google TTS engines. All these enginesoffer high quality voices but not all of them are Neural text-to-speech voices.Neural TTS is a new type of speech synthesis powered by deep neural networkswhich produces synthesized speech nearly indistinguishable from the humanrecordings.
Currently Amazon Polly provides approximately 15 neuralvoices and about 60 standard voices in almost 30 languages. Here is the link tothe complete list of voices provided by amazon polly: https://docs.aws.amazon.com/polly/latest/dg/voicelist.html
Microsoft provides around 70 neural voices and even a highernumber of standard voices in about 50 languages. Here is the link to thecomplete list of voices provided by Microsoft Azure: https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support#text-to-speech
Google provides around 251 voices, using standard andWavenet technology in about 40 languages. Here is the link to the complete listof voices provided by Google: https://cloud.google.com/text-to-speech/docs/voices