Studio Voice (audio enhancement)
Getting started
Studio Voice uses AI to enhance your audio. It removes background noise, boosts its volume, and gives it a studio-quality finish.
You can use Studio Voice on any video that has a microphone recording:
Screen + camera
Camera-only
Screen-only (with microphone)
Studio Voice can't be used on screen-only videos where you didn't also record your microphone.
Studio Voice is also available for external video files that you upload to Tella. Just keep in mind that Studio Voice is optimised for enhancing speech and not other types of audio, e.g. music or sound effects.
Using Studio Voice
Enabling
To enable Studio Voice, open a video in the editor then click on Setup from the left-hand toolbar.
In the Setup panel you'll see the option called Studio Voice. Clicking on the switch will start generating an enhanced version of your audio.
When you enable Studio Voice, you're enabling it for the entire video. So the audio for all the clips in your video will be enhanced.
Generating
Depending on the duration of your video it can take a few minutes for the enhanced audio to be generated.
While it's generating you won't be able to play or edit your video, but you can record or edit other videos while it generates in the background.
Once the enhanced audio has been generated, the editor will update and use the new audio. Play back the video to hear the difference.
When the enhanced audio has been generated you may notice a decrease in the quality of your video. This is because Studio Voice uses low-res video files in the editor. These low-res video files are only used while you're editing. When you share or export the original high-res video files will be used. ✨
Disabling
You can switch off Studio Voice whenever you want — just click on its switch in the Setup panel. Once the enhanced audio has been generated you can toggle it on and off without any waiting time.
Adding additional clips
If you add new clips to a video that has Studio Voice enabled you will need to wait for the enhanced audio to be generated before you can edit, share or export.