Our Text to Speech feature is designed to be user-friendly and seamless, empowering authors to create immersive and accessible courses effortlessly. Through audio and voiceover capabilities, we aim to make your course content more engaging, impactful, and inclusive for learners worldwide. Authors can click the Generate Audio button to convert selected text into clear, natural-sounding audio.

Benefits of Text-to-Speech (TTS) in Course Creation

Accessibility and Inclusivity: With TTS, you create a more inclusive learning environment, allowing visually impaired learners or those with reading difficulties to access course content through audio.
Enhanced Learning Experience: TTS allows for multimodal learning, combining visual and auditory cues, catering to diverse learning styles and preferences, and boosting retention.
Time and Cost Efficiency: Save time and resources by automatically generating audio without manual voiceover recording, making the course creation process faster and more streamlined.
Global Reach: By supporting multiple languages and accents, TTS enables you to reach a global audience, breaking language barriers and fostering international engagement.

Who Can Access Text-to-Speech

The Text to Speech feature is available to our Trial, Team, and Enterprise clients. For our Free and Pro plan users, it will be available as an add-on feature, so you will need to click the Request a Demo button to proceed with enabling this feature.

How to Use Text-to-Speech

With Text to Speech, you can easily convert up to 3,000 text characters into audio. This allows you to narrate sizeable sections of your course content, making it more accessible and engaging for your learners.

You can access the Text-to-Speech functionality through the content options:

A narration block
Single audio content block

1. Paste the text into the Your text field, and type the audio title.

2. On the right, under the Voice settings, select the AI engine you would like to choose for generating the voice.

You can select between ElevenLabs and OpenAI.
Note: ElevenLabs is selected by default as it allows you to choose different accents.

3. Choose your language, voice, and playback speed - to adjust the speed, click the bar below the speed option you want to set.

Click on the tab below to learn more about this topic.

How to edit Tonality and Playback Speed using ElevenLabs

For English, Easygenerator uses the ElevenLabs Turbo v2.5 model, which allows authors to adjust the playback speed directly from the Voice settings.

For other languages, the Eleven v3 (alpha) model is used. In this case, the playback speed option is disabled, but additional expressive controls are available. You can influence pacing, emotion, and delivery by adding audio tags directly in the text editor.

For example, inserting [fast] or [slow] affects speed, while tags such as [laughter] or [crying] add emotional cues to the audio.

4. Once you’ve set the provider, language, voice, and playback speed, click Generate audio to preview how it sounds.

5. At the bottom of the window, you can pause, scroll through the audio preview, and check the length of the audio.

6. If satisfied with the result, click Save and add audio at the top right. If not, adjust the settings to your liking and click Generate audio again.

Once the text is converted into audio using TTS, the generated audio files will be automatically saved in your Easygenerator library. You can reuse the audio for different courses or modules, saving valuable time during content creation.

Note: If you encounter any issues, click the Generate Audio button again to get the desired output.

Edit Text-to-Speech

You can edit the text, voice, speed, and title of the audio created with Text to Speech from the narration block, single audio content block, and from the audio library by clicking

Once all changes are made, click the Save changes button.

NOTE: The updated version will replace the original one.

Text-to-Speech Audio in Translated Courses

When a course is translated using automated translation, the TTS audio will also be automatically translated into the selected language—including the text used in the original TTS audio. Each translated course has its own translated audio, which is independent of the original (or "master") audio.

This means that any changes made to the translated TTS audio will not impact the original version, and vice versa.

What Happens If a Language Isn’t Supported?

While most languages are supported by our providers, some languages are currently not supported. In these cases, Easygenerator will retain the original (master) audio in the translated course.

It's important to note that when you use text-to-speech to create audio, it is saved in your media library within your Easygenerator account. This audio—referred to as the "master audio"—is the file used in all course duplicates and also appears in translated versions if TTS is not available for the target language.

In that case, if you need to make changes to the audio in a translated course that uses the master audio, it’s best to delete the existing file and create a new one from scratch using the translated text and text-to-speech. This ensures that the master audio in your media library remains unchanged and that all other courses using it are not affected.

Security in Text-to-Speech

You can check all security details on the Text-to-Speech functionality here.