Avis clients sur Descript

I love how easy it is to edit audio using the auto transcription. It allows for other great features like filler word and word gap detection/removal. The integration with Zapier allows us to import new media, and the publishing integrations allow us to export to hosts and other apps we use in our clients workflows.

For more advanced editing, I wish there were integrations with Adobe Audition that would make it easy to locate spots that have been commented on and then reimport or sync the changes. For our workflow, I would also love if we could utilize an API to directly integrate Descript with our workflow rather than needing to utilize Zapier.

1. Descript's key feature is how it transcribes your audio and converts it into an editable word document. I was astounded to discover how simple it was to effectively cut and paste words while simultaneously moving the audio waveforms.
2. It makes use of the Google speech to text engine, which has been demonstrated to be the market leader in numerous studies.
3. Transcripts are attractive and are designated by individuals. With just one click, you can securely send transcripts with video or audio.

1. It becomes slow with time, and you must pay to utilize it on a regular basis.
2. Although the automatic, entry-level version of Descript has a transcribing accuracy of roughly 95%, there are still grammatical problems.
3. It takes longer than I expected to look over transcriptions and revise them later, so I have to spend more time correcting the transcripts even during my working hours.

The quick auto transcription was really a game-changer for editing audio.

There was a little learning curve for figuring out playback, but they've since fixed it.

The ability to edit an interview or podcast just by editing the text is incredible.
The workflow is fairly straight forward – import audio file, choose how to transcribe, wait…, edit the transcript & audio in various ways, export or publish as needed.

The automated transcription is good, but not great. There are always little errors that seem obvious to a human – capitalize the first letter in a sentence, don't capitalize a word in the middle of a sentence, abbreviate doctor as Dr. when a name follows, etc. – and they seem to always show up, even when they've been corrected previously, so it's unclear whether the 'machine' is actually 'learning'.
The app appears to not be built as a native app for macOS which means it lacks certain core features. The most annoying to me is that the window always opens in the default size (i.e. small) and never remembers the sizing or positioning that I choose every time I open it.
The developers are rapidly adding features, but almost too quickly. Once I get used to a feature or function, it doesn't take long for the menu item to be changed or moved (Share, Export, Publish all do similar–though different–things, and have each had their turn as a unique menu item or being grouped together in various ways). I got very efficient at correcting the transcription (which, unfortunately, must be done frequently) until they changed the entire process of editing the transcript.

A Google Docs-like editor for modifying video literally feels like living in the future. I am not a professional video editor, and so I find it incredibly useful to be able to my own quick edits and rough cuts - especially for video content for social.

I occasionally find that it is hard to get it to do exactly what I'm trying to do - which is the downside of such a powerful intuitive interface - if you don't want to do the obvious thing, it can be challenging to figure out how to work around (e.g. splitting audio and video tracks etc). But these are minor niggles.

The product is pretty easy to use straight off the bat but its when you get the transcripts back that things really get interesting. The way the text and audio/video files are linked is totally special. You can change one and the other follows. You can copy and paste text and the media comes along too. Once you've compiled your rough you can export

Software feels a bit slower and bloated now due to the addition of the editing features - and a bit more sensitive to handle. I have to be more accurate when I click!

Transcription, text search, the ability to use the software effortlessly means this is a crucial piece of software to me both personally and professionally. I love the feature of after transcription, clicking on a word and playing the video from there, such a simple feature but I am sure was very hard to implement from a programming perspective.

I think it would be great to see a thumbnail overview of projects currently being worked on, having that option as well as list view would be very helpful to me. Sometimes the software can be buggy in terms of asking something to be transcribed and it says this cannot be completed at this time. The other thing I like least is after you've imported multiple files and transcribed them, the software can re-order them, then the videos and transcription are out of sequence, there is no easy way to re-order them and get them to where you want them to be.

Using the transcription to edit audio and video completely changes the game - so much time is saved by being able to use the text to guide exactly when to clip.

Responsiveness is still a bit laggy, and compared to other multi-track editors, this still feels at times unwieldy. Transcriptions could also be more accurate, as going through and changing them can take quite a lot of time.

I really like that as a person with no audio or video editing experience, I can create useable short audio and video content for social media, websites and for sharing information. I no longer have to outsource this editing work to Fivrr.

As the product grows and more features are added, it become harder to learn the system if you have no editing background.

The killer feature of this product is the ability to edit text and audio or video simultaneously. You can edit each and the other immediately updates, so it's possible to "read" your entire show as well as edit in depth by words or by frames or samples when necessary.
It's wonderful to have the whole project in the cloud with comments shared like a Google Doc for collaboration.
The automatic transcription works pretty well with clear speakers.
Exporting to audio files or DAW projects works well.

The automatic edits at word boundaries can be a little rough and need hand touching up.
Sometimes the software needs to be restarted to take into account a new update.
Occasional slipping of time or data due to software updates or collaboration.
Could still use a "stem" export function in addition to flattened audio and DAW projects.
It would be great to improve automated transcription further, but this is a hard problem.