How to convert speech into text

You can easy convert English speech into text on your PC.
This manual works for all Windows (WinXP-Win10).
1.Install VoiceMeeter, VB-CABLE.
Download and install VoiceMeeter.
or using a direct link
Download VB-CABLE.
or using a direct link
Extract all files and Run Setup Program in administrator mode. Reboot after installation.
2.Install Python. Choose the suitable version for your Windows.
(the latest working version for WinXP is 3.4.3).
3.Add Python, PIP to system PATH.
PIP is the package installer for Python.
Checking if PIP is added to your PATH variable
Let’s start by finding out where we stand. If you don’t know if your PIP installation is added to your PATH variable, you can find it out easily by using a certain command at a CMD prompt.
Knowing this will point you in the right direction and save you from trying out unnecessary steps.
Note. If you already know if the path of your PIP installation is added to your PATH variable, move down.
Here’s a quick guide on checking if the PIP installation is already in your PATH variable:
Type pip –version and press Enter.
Press Windows key + R to open up a Run dialog box. Then, type “cmd” and press Enter to open up Command Prompt.
Inside the command prompt window, type echo %PATH% and press Enter to get a listing with all locations added to the PATH variable.
If you manage to find a path similar to C:\Python34\Scripts (the number depends on your Python version), it means that the installation path is already added to your PATH variable.
If you weren’t able to find the PIP installation path using the test above, move down to the next methods below to add PIP to the PATH environment variable.
Adding PIP to the PATH environment variable using the Windows GUI
If you revealed that the PIP installation is not set to the PATH as an environment variable and you already installed the Python distribution, you’ll need to do it manually.
After completing the procedure below, you will be able to input PIP commands from a Command Prompt window. Here’s a quick guide on Adding the PiP installation to the Path environment variable using the Windows GUI:
Press Windows key + R to open up a Run dialog box. Then, type “sysdm.cpl” and press Enter to open up the System Properties screen.

Inside the System Properties screen, go to the Advanced tab, then click on Environment Variables.
In the Environment Variables screen, go to System variables and click on Path to select it. Then with the Path selected, click the Edit… button.
In the Edit environment variable screen, add the path where the PiP installation is located. For Python 3.4, the default location is C:\Python34\Scripts.
Type it in the form

4.Update PIP.
It’s necessary if you have old Windows.
Type in cmd
python -m pip install –upgrade pip
(use the next command for WinXP pip3 install –upgrade pip==19.1.1)
5.Install a speech recognition toolkit Vosk.
Type the next command in cmd.
pip install vosk
pip3 install vosk
Install sounddevice
pip install sounddevice
6.Clone vosk-api and vosk-model.
Download and extract vosk-api.
Download and extract vosk-model.
Go to the folder where you extracted vosk-api, go to the subdirectory vosk-api/python/example, and copy an extracted vosk-model to there.
For example if your vosk-api located in C:\vosk-api-0.3.38 Then copy an extracted vosk-model vosk-model-small-en-us-0.15 to C:\vosk-api-0.3.38\python\example
Rename the folder vosk-model-small-en-us-0.15 to model.
7.Run a speech recognition program.
Now you can open cmd and navigate to the subfolder vosk-api/python/example. In our example it’s cd C:\vosk-api-0.3.38\python\example and type python
I recommend you to create a .bat file to run the program with one click.
Use the next method to do it.
1.Create a .txt file in vosk-api/python/example, give it a name speech-to-text.
2.Open the file in Notepad. Add the next command to the text field
3.Click File -> Save as
In the menu File type choose All files. Now add an extension .bat to the file name.
Save it as speech-to-text.bat
You can download a ready-made file, extract and copy it to vosk-api/python/example.
4.Run it whenever you need speech recognition. Create a shortcut of the program and copy it to your desktop.
4.Change settings for Speaker and Microphone.
Right-Click on the volume icon and click Open Sound Settings.
Choose “VoiceMeeter vaio” for Speaker and Microphone.

5.Set two outputs in VoiceMeeter.
You have to keep VoiceMeeter opened whenever you want to have two outputs.
C:\Program Files\VB\Voicemeeter\voicemeeter.exe
Find a menu HARDWARE OUT. Click A1 and choose VB-Audio point. Click A2 and choose your Speaker (HD Audio rear output).

Now we have two outputs. One is for virtual cable which restream a sound from Speaker to Microphone. Another one is for our everyday Speaker
6.Listen to any audio content.
Listen/watch everything what you like from videos on your hard disk to online YouTube clips in English.
The program will convert speech into text.

Register in our website and we will help you to pick up the best material to improve your English rapidly.

WP Radio
WP Radio
Easy English Study
× You can message on WhatsApp