TTSAutomate 3.1

Text-to-speech engines and tools are of great help for anyone having audio as the preferred output, such as persons with a severe visual impairment.

TTSAutomate offers anyone interested in transforming text into audio using synthetic speech a flexible tool capable of supporting and a wide array of languages and voices to produce high-quality locations that you can then play back or/and save as WAV or MP3 audio files.

This open-source solution uses phrases as their basic unit, rather than paragraphs or full documents (though nothing prevents you from pasting a full paragraph into a Phrase box). Each phrase unit will produce a separate audio file using the voice and the language of your choice. Note that voices are not selectable by a phrase, which means that all phrases on the list will be read by the same TTS engine. This is important if you wish to create dialogs with different characters and genders and to allow the program to read texts in different languages correctly.

Though designed to look like a simple and straightforward utility, it is advised that you read the scarce – yet useful – instructions provided in the program’s GitHub page if you want to reach the desired results. The program lacks information about how to go about the different buttons and, most importantly, the order in which the various steps required need to be taken. To make things a little more difficult, TTSAutomate showed an annoying tendency to crash during my extensive tests.

Once you get the hang of it, though, TTSAutomate proves to be a highly useful and versatile tool to produce high-quality recordings of selected phrases in a wide variety of male and female voices in Czech, English, French, German, Portuguese, and Slovak. Phrases can be edited at any time and re-built with the voice and in the output format of your choice. Being an open-source development, it is certainly a tool worth trying, though it seems to require still some extra work to make it more robust and to improve its lacking documentation.