Text-to-Speech (TTS) in EasyVideo lets you instantly convert written text into natural-sounding audio, powered by OpenAI technology. Whether you're adding narration, giving instructions, or improving accessibility—TTS makes it fast and simple.
How to use Text-to-Speech
Enter your text in the input box
Notes:
You can add custom pronunciation to specific words by selecting the word and clicking on the speaking icon at the bottom. Then, spell the word as you'd say it. Example: Uh-doe-bee for Adobe or eye-land for island.
Also, use the clock icon to add pauses to your script. Pauses start by default on 0.5s, but you can click on it to change the time. Choose your preferred language and voice.
You can listen to the audio before generating it by clicking on the play button below the script.
Click on Add audio
Your audio file will be added to your media library and placed on the timeline, ready to be edited or synced with visuals.
Note: Here’s a list of the supported languages for voiceovers in EasyVideo.
Why use Text-to-Speech?
Add voiceovers without needing to record audio manually
Improve engagement and clarity in your videos
Best practices
Use TTS to narrate step-by-step instructions, explain visuals, or replace placeholder voiceovers
Need to make changes? Just click on the audio in the timeline, edit the text, and click on Apply changes.
