Guide

Guide > Editi...creen > Slide...rties > Narration > AI Voice

AI Voice

Edit screen > Slide Properties on the right > Narration > Type:AI Voice

Voice

Edit screen > Slide Properties on the right > Narration > Type:AI Voice > Voice

You can change the AI voice. Select the entire slide to change the voice for the whole presentation, or apply a different voice to each slide individually.

You can search and apply the AI voice you want by language, emotion, age, gender, etc.

Table of contents detailed information

Videostew uses TTS provided by ElevenLabs, Humelo, Google Wavenet, Amazon Polly, Naver Clova, and Microsoft Azure.

You can set up complex search criteria based on each engine, such as gender, age, emotion, atmosphere, and language, allowing you to quickly find the voice you want.

Pro Tip: Each slide will have AI-generated voice. Follow the guidelines to ensure each slide has a completed sentence. Use the enter key to provide line breaks and apply [text appearance effects] to create a natural flow.

Provided languages

Korean, English, Chinese, Spanish, Hindi, Arabic, Bengali, Portuguese, Russian, Japanese, German, French, Turkish, Malay, Tamil, Thai, Vietnamese, Urdu, Persian, Italian, Thai, Gujarati, Polish, Ukrainian, Dutch, Greek, Swedish, Romanian, Hungarian, Danish, Finnish, Slovak, Norwegian, Hebrew, Malay, Czech, Bulgarian, Slovenian, Lithuanian, Latvian, Estonian, Croatian, Malayalam, Kannada, Welsh, Irish, Basque, Icelandic, Swahili, Filipino, Mongolian, Maltese, Catalan

Speed

Edit screen > Slide Properties on the right > Narration > Type:AI Voice > Speed

Change the reading speed of AI voice. Generally, readers prefer a speed of 120% - 130%, but it can vary depending on the characteristics of the AI voice, so you can decide while pre-listening.

After regeneration

Edit screen > Slide Properties on the right > Narration > Type:AI Voice > Mute after playback

You can use this when you want to read all the AI voice in one slide and add a slight pause. By setting the time to around 0.5 seconds, you can prevent it from moving to the next slide too quickly.

Conversely, if you think the mute time increases when moving to the next slide, you can set it manually. It supports up to -0.2 seconds, and generally, -0.1 seconds will give a slightly faster transition.

Manual text placement

Edit screen > Slide Properties on the right > Narration > Type:AI Voice > Manual text input

When you enable the automatic text designation toggle, you can adjust the content to be read however you want, independent of the text shown on the screen.

It is generally used when you want to display only the words on the screen and read the detailed content separately, or to adjust the pronunciation.

Playback Time

Edit screen > Slide Properties on the right > Narration > Type: AI Voice > Playback time

If the AI voice does not reach the end due to a network issue, or if the voice length is not calculated correctly, press the "Recalculate" button to regenerate the AI voice and reset the duration of each slide.

Slide Repeat Playback

Edit screen > Slide Properties on the right > Narration > Type: AI Voice > Slide repeat playback

When you enable the slide repeat toggle, the same sentence is read repeatedly when it appears in multiple slides.

For example, it can be used when intentional repetition is required in educational videos.

Voice Cloning

Edit screen > Slide Properties on the right > Narration > Type:AI Voice

In addition to the AI voices provided by Videostew, you can directly create and use TTS that has learned your voice.

You can start recording your voice by clicking the 'Add' button on the custom tab. You can record in real-time on the website, or you can upload a pre-recorded file.

When recording, reading just five sentences is sufficient. When uploading a pre-recorded file, please upload an audio file that is longer than 15 seconds.

The reason for using voice-cloned TTS is to present a natural-sounding voice. Therefore, it is more effective to create a natural TTS without using professional recording equipment. It is also beneficial if the speaking style you frequently use comes out naturally. If you plan to create conversational content, please record a naturally conversing voice.

The cloned voice is tied to the workspace. If you want to use the AI voice you created in another workspace, press the Settings (▼) button next to the Add button and bring the voice you own to the other workspace via the “Import Voice from Another Workspace” button.

[Stop]