SpeechToText Pro is an easy way to convert your spoken words into text on your Windows 10 Mobile or Desktop device. This app combines Cortana’s voice recognition services and remote web services for more accurate conversions, and this lessens the impact on your system’s resources making it quite light weight.
For a speech to text app it has minimal layout, with most of its features convered in one screen.
It can recognize most of the words that a user can say in a language that has Cortana support and is optimized for short phrases. Presently, Cortana is available in English, Chinese (simplified), French, German, Italian, Japanese, Spanish and Portuguese. Cortana is also optimized for several regions associated with these languages.
Even specific names of people, places, events, products and concepts are recognized and there is support for punctuation. For example, the phonetic transcription of “the global average surface temperature rose point six to point nine degrees celsius comma or one point one degrees fahrenheit period roughly thirty percent of incoming sunlight is reflected back into space” is captured as ‘The global average surface temperature rose .6 to .9 degrees Celsius, or .1 degrees Fahrenheit. Roughly 30% of incoming sunlight is reflected back into space.’ Not bad!
The generated content can be edited, copied to the clipboard with a single button click, saved as an HTML or text file, opened from a previous save to continue from where you left off, or sent as an email. It can also be played back with a male or female Cortana voice that is capable of inflection.
SpeechToText Pro has a free trial version with the full version of the app priced at $2.49.
Good speech to text software lets you bypass typing. If you write articles, eBooks, website content or many emails, SpeechToText Pro can save you many hours each month. Because voice recognition is done by remote web services that then return the result to the device, an internet connection is required by this app. The benefits are a light footprint on your device and improving accuracy over time as the remote web services gain experience with a wide variety of users’ voices.