Create a recording

• Go to https://cloud.google.com/text-to-speech
• Scroll down to "Put Text-to-Speech into action"
• Select en-US-Wavnet-C
• In the "Text to speak" box, delete the example text and type in what you want
  • Sometimes you need to misspell things to make them sound correct.
• Click the "Speak It" button
• Use a program like OBS Studio to record the audio so you can capture it

You now how a video clip that has the audio, manipulating the audio is next.
To make it sound more ADA like we need to install Audacity and a plugin

Install Audacity program

• Download and install Audacity from here: https://www.audacityteam.org/download/

Install FFmpeg for Windows

• Open this link in your browser and follow the instructions
• file:///C:/Program%20Files%20(x86)/audacity/help/manual/man/installing_ffmpeg_for_windows.html
  • ----> ffmpeg-win-2.2.2.exe

Install Plugins

• Download Multi-Voice chorus plugin for Audacity
• https://forum.audacityteam.org/viewtopic.php?f=42&t=68007
• THIS LINK -> https://forum.audacityteam.org/download/file.php?id=6115
• The plugin needs to be saved to:
  • C:\Program Files (x86)\Audacity\Plug-Ins
• Open Audacity
• Tools > Add/Remove Plugins
• Locate MultiVoiceChorus and select it
• Click Enable
• Click OK

Add Audio Effects

Now you can open that video recording from OBS Studio that has the audio you want to manipulate

• Open the file with the voice you want to manipulate
• Press Ctrl + A to select the recording
• Effect > Multi voice chorus
  • Speed: 1.90
  • Depth: 2.90
  • Voices: 1
  • Mix: 3.40
• Effect > Delay
  • Delay type: Regular
  • Delay level per echo (dB): -18.70
  • Delay time (seconds): 0.00
  • Pitch change effect: Pitch/Tempo
  • Pitch change per echo (semitones): -0.120
  • Number of echos: 2
    Allow duration to change: Yes

Export the Recording

• File > Export As MP3/WAV/OGG
  • I suggest exporting to these three separate formats as different programs use different files and it can save you time in the future