VOVSOFT - Speech to Text Converter

Speech to Text Converter provides two applications in one: an audio recognition tool and a text translator. What it actually does is take an audio file as input, convert the audio to text and then translate the output to the target language.

Unlike other applications of its kind, Speech to Text Converter does not rely on one of the well-known translation engines to carry out its tasks. Instead, it supports the IBM Cloud Speech to Text API. In other words, it provides a desktop application for IBM Cloud users that extracts audio from a file and turns it into text, also performing a language translation in the process.

The simplest interface layout greets you as Speech to Text Converter is launched. The main window only comprises a field where you can browse for the input audio file and another to select the target language. A few large buttons in the toolbar are available to offer basic functionality: opening a file, saving the output to a text file or accessing the settings.

Speech to Text Converter can load an audio file located on your computer, supporting common formats, such as MP3, FLAC, WAV, OGG, WEBM. Alternatively, it comes with a built-in recorder, which enables you to create a new audio file on the spot. Evidently, the computer needs to be equipped with a microphone to be able to use the recording function.

As soon as you hit the “Convert” button, Speech to Text Converter navigates to the Settings area, prompting you to enter the IBM Cloud Speech to Text API key. With a single click, you can go to your IBM Cloud account to get the key you need.

The Speech to Text Converter application is only useful if you are already an IBM Cloud user. The Speech to Text API key is mandatory for the converter to work. To put it another way, it cannot be used freely by anyone, as it is designed specifically for those who own an  IBM Cloud account.