Text-to-Speech (TTS) Features

Text-to-Audio Conversion

A guide on how to convert text to speech with Moknah

Based on the interface shown in the image, here are the steps to generate audio using the text-to-speech feature:

Enter text : Type or paste the text you want to convert to speech into the large input box.
Note : There is a 1,500-character limit per request for this tool.
Select a voice : Click the drop-down menu labeled "Select a voice." You can search for specific voices by name, language, gender, age, use case, or accent.
Setting up the mode (optional):
Standard Generation: Leave the "Enable Emotions & Dialects Mode" box unchecked for a stable and professional narrative.
Emotions & Dialects Mode: Check this box if you want to control specific emotions or use regional dialects.
Tip: If applicable, use curly brackets for emotions—such as {Shouting}—and ensure the tone of the text matches the tone of the selected voice.
Select the normalization mode : Specify how you want to process the text:
Basic Treatment (1 credit) : Standard treatment for natural speech flow.
AI-Enhanced Processing (2 credits) : Advanced processing that includes typo correction and refinement (recommended for complex texts or Arabic).
Generate : Click the blue "Run" button at the bottom to generate your audio.
Additional option : You can click the "Voice Settings" button near the top left to adjust advanced parameters, such as speed or stability, before generation.