One of the most common tasks that journalists, bloggers or writers have in general is to translate what is said in an interview, recording and any audio in which they talk about a topic into text. This is a somewhat complex activity that involves listening, memorizing, transcribing, going backwards the track, advancing, clarifying the audios to focus the voices, etc., to make this activity a little easier, a Gnome player called Parlatype is born.
What is Parlatype?
Parlatype is a simple audio player that allows us to manually transcribe audio to text in a simple and very efficient way. It is developed using the C language and works perfectly in the GNOME desktop environment.
The simplicity of the tool allows it to run on any computer, resource consumption is minimal, ease of use is incredible, and your development team is constantly updating the tool.
Parlatype Features
The application has a series of features that helps make voice-to-text transcription more to less, highlighting the following functionalities:
- It has an interface that allows us to visualize the waves of the audio in question, highlighting the pauses, points and voices, this allows us to transcribe the audio following the gaps in the audio.
- You can adjust the audio playback speed according to your preferences.
- One of the features that I like the most about this tool is that every time we pause the audio, it goes back a few seconds, which allows us not to lose the thread of the transcription when it is played again. (you can adjust this option).
- Parlatype has an excellent integration with LibreOffice, so lovers of this office suite will have many more features, however, we can use any office suite when transcribing.
- It has great compatibility with most of the current audio formats, since it comes equipped with the GStreamer framework.
- Integration with multimedia keys.
- Adjustable interface.
- Support for multiple languages.
- A large development community and very detailed documentation.
- Free and open source.
How to install Parlatype?
Parlatype has official support for Ubuntu and derived distros, the installation is quite simple, we just need to install the tool's PPA and then install the application with the following commands:
$ Sudo add-apt-repository ppa: gabor-karsay / parlatype $ sudo apt-get update and & sudo apt install parlatype
Finally run the tool and start enjoying.
Users of other distros can try Parlatype by following the installation from its source code to do so, execute the following commands:
$ git clone https://github.com/gkarsay/parlatype.git
$ cd parlatype
$ ./autogen.sh --prefix=/usr --disable-introspection
$ make
$ sudo make install
When trying to install the PPA, the following message appears: 'This PPA does not support xenial'.
Obviously, I won't be able to enjoy Parlatype on my Mint 18.1
A pity.
the ppa gives many problems, better compile it, this advice I give you because your friend popeye I am… ..
sudo apt-get install build-essential automake autoconf intltool libgirepository1.0-dev libgladeui-dev gtk-doc-tools yelp-tools libgtk-3-dev libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgtk-3- 0 libgstreamer1.0-0 gstreamer1.0-plugins-good
wget https://github.com/gkarsay/parlatype/releases/download/v1.5.1/parlatype-1.5.1.tar.gz
tar -zxvf parlatype-1.5.1.tar.gz
cd parlatype- *
autoreconf
./configure –prefix = / usr –disable-introspection
I prefer the prefix in ~ / .local
make
sudo make install clean
and to uninstall:
cd parlatype *
make uninstall
Thank you for sharing this software.
When I read the headline in the RSS I expected it to go from voice to text by itself and that you only had to correct errors.
Using Julius, CMI Sphinx, Open Mind Speech, Vox Forge, or even Google
In its day I tried to use this software and it was very cumbersome, and not productive at all, nowadays you can dictate to the google browser or its document application and it writes it to you quite well, even from a tablet or mobile, but I think it is about make (and I thought it was about that) an apk that would convert your recordings to text or a desktop application.
https://github.com/katchsvartanian/voiceRecognition
Use the Google API for speech to text from FLAC files.
Looking for voice recognition programs from an audio file, caused by reading this article, it seems that there has not been much progress since years ago I became interested in the subject, with the exception of this needle in the haystack, which I share because a lot it has been difficult to find something new.