Improve paragraph detection
Descript currently is being overly aggressive with paragraph detection. It's inserting paragraph breaks without even adding punctuation like full stops. So you get lots of hanging paragraphs with no terminating punctuation. And listening to it, there doesn't seem to be any reason for splitting the paragraph.
Include filler words
Add option for filler words to be included in the transcript to be able to remove them from the audio using the audio editing tools.
media lib across projects
would be nice if had a common media lib for all projects... avoid having to add same music and bumpers for every project.
Shorten silences in a Composition
Equivalent to 'smart speed' in podcast players, offer a non-destructive process to shorten detected silences. Speakers sound more confident, dialogue flows more smoothly for inexperienced speakers. Analysing the waveform to determine the difference in volume between 'speech' and 'silence', you'd be able to offer users the ability to shorten any silence of at least, say, 300ms down to 50ms. Adobe Audition offers this destructively with Detect Silence; Ferrite for iOS non-destructively with Tighten.
Would be great to be able to use this on the ubuntu desktop. I would also work for chromebook too.
Global volume balance
If you have a project that contains multiple people speaking at different volumes (db), having a way to set the average volume of all speakers to be equal would be great for consistency. That way you avoid going from loud to soft to loud to soft.
Ability to split video and audio track
I want to replace the audio in a section with better audio. Right now video is black instead of my screen recording. I wish I could split audio and video for segments so I can replace just the audio and keep the video.
nasal voice correction
Correcting the voice of people with a nasal disorder could be a unique selling proposition, benefiting Voice Double or any other AI / Deep Learning-based solution with a new target market. Either Voice Double corrects the voice or just searches for a voice that is similar to the vocals but does not sound nasal. From an ethical point of view, it is only a remedy for chronic diseases / dysfunctions such as hypersensitivity or blocked or severely curved nasal septum, less for voice changes or morphing. Furthermore, such a solution could be written off as a prescription (e.g. via German Heath Care System), or at least as a work-related financial expense, which would increase sales for you. What do you think about this request? Koushik Sikdar, Germany