Feature Requests

In my current projects with Avatar, there's no natural pause between the sentences it reads—the AI speaks continuously without a break. I’d prefer not to insert gaps or scenes between the current ones, which causes the screen to black out and creates a visually jarring result. It would be great to have audio blocks with export functionality and settings to adjust the reading speed slightly. Additionally, adding controls to insert natural pauses or "breathing spaces" between sentences would significantly improve the flow. Lastly, I'd like to have the ability to set the duration between scenes manually, so transitions feel more intentional and smooth.

(Maybe it could be combined to the "custom filler words list" idea.) For now, remove filler words is only available in English. I like the fact that it changes color in English. I'm pretty sure it's doable by just changing the internal list. We could create a post for listing common filler words in our languages so that you don't have to research them.

Hi Descript team, I’d love the ability to train an AI Speaker directly in French. Currently, training with English text results in my AI Speaker reading French scripts with an English accent. Would it be possible to add support for recording AI Speakers using non-English training texts? This feature would be incredibly valuable for multilingual users. Thank you for considering this!

Do you plan support for Russian language?)

Feature request for the ability to adjust the speed of generated Overdub audio. Looking for Controls to speed up / slow down the cadence. Ability to adjust the spacing between words and / or phrases.

I would kill to be able to record my screen of google slides or powerpoint so that I can record myself doing the animations while the ai generated voice is playing so I can time it with the generated audio. In other words, I want descript to play the AI audio while doing a screen capture where I can make the animation transitions as that AI audio is playing. I don't see an easy way to achieve this without having to record the video with the audio playing outside of descript and then uploading the video back into descript.

I occasionally encounter recordings with bad audio and use a lot of regenerative AI to fix it, but I don't need all the other features that come with a business account. It'd be great if you could buy more regenerative audio credits by themselves!

Can I purchase additional dubbing time?

I want you to support Japanese.