Now some of the removed parts sound really hard and harsh, making the transition using fade-in and fade-out features would smooth that out.
This is a bad filler world that would be helpful if it was removed
If users would define their language maybe that would help the AI to be more consistent in its editing. Now it feels like English is the default and it needs to guess what other language is used.
Sometimes, filler words or hesitation add emphasis to a discussion - perhaps a new feature would be to not only edit the transcript text - but to also edit the same text in the audio (by keeping or removing the corresponding audio)
Please make it so that when we log in we don't have to reset the configuration every time. Thank you!
Since you now have the ability to detect different speakers in the same track, it would be nice to add the ability to split speakers to separate tracks for separate mixing. You could also use this same feature to remove bleed from recordings where multiple people are on separate mics in the same room. De-bleed and separating speakers to their own tracks would each be extremely valuable new features for you to add.
I would love the ability to choose how many seconds I want long deadair shortened to, or least a few options. I prefer to limit silences to 2 seconds instead of 5.
I recently had an issue where I uploaded and processed a single audio stream, custom selection to remove background noise only. I loaded the resulting export back into my DAW. The dialogue in this stream had lost its alignment with other parts for the project. I noticed the sample rate was different to the original (also an issue that needs addressing!) But that wasn't causing the issue. CV had removed space along the way, leaving timing issue which I had to re-edit.
Automate the process for uploading and processing of recordings.
Being able to create specific folders for specific projects.
export OMF files for adjusting the edit points in Pro Tools?
Hallo Adrian,
ist es mögliche einen Google Drive Ordner zu verknüpfen.
Meine Zeencaster account lädt ein File Hoch dein Cleanvoice nimmt ihn und bearbeite ihn mit immer den selben Einstellungen. und legt ihn wieder ab selber name nur mit clean ergänzt?
When uploading 2 tracks that have mic bleed, have the option to mute sections of mic bleed. That's something I have to go thru and edit out in my recordings, so it'd be SO GREAT if clean voice could take that task off my plate.
I often use the same settings when uploading a track, which I would like to save as a custom template.
Additionally, uploading multiple tracks to process with the same settings at the same time would save a lot of work. Currently this can only be done one by one I think.
Gibt es bzw. wird es möglich sein, eine individuelle Liste von Füllworten bei einem Job anzugeben? Ich habe hier nämlich eine Aufnahme, in der zu oft das Wort "sozusagen" fällt, aber Cleanvoice rechnet das nicht raus.
Here's my feedback:
This product would be amazing and widely adopted by tons of creators if you could upload video and have the same result.
Hi I have recordings of talent in a studio to submit as a sample, have the system match that sound and tone from home recordings.
Being able to export the finished Audios in separate tracks and AAF Format to see the actual cuts and to maybe fine tune, if necessary.
I like your service, but I really need russian for my targets. Please, help me!
I believe it would be convenient if "Custom" processing profile settings were persisted across uploads.
Get automated messages to slack once processing is finished.
I would love a "magic wand" which removes the occasional mouth click within words, ditto something which can remove "vocal fry" from F and S sounds but leave the F or S sound intact, and not sounding "weird' afterwards.
So far I've noticed that when using it to edit out filler words (uhh, ummm) etc it cuts words abruptly. Moreover it sometimes doesn't recognize actual isolated filler words that are very noticeable and instead it just chops phrases that shouldn't be cut. Leaving behind a lot of pops and artifacts as well as damaging the original content.
I was using the multitrack option for a 45 mins podcast with 2-3 synced tracks and instead of saving me time I had to go through and fix all the artifacts (and ignored filler words) anyway.
I'd like a feature where there is an option to have two audio download options, one file with "mute only" selected and another file with the edits removed from the audio. It would be very helpful to have that done in the same process.
When I processed a talk from a conference, the applauds from the crowd at the end were removed. I would prefer to keep them in the audio :)
Excellent service! Thank you!
I just want to have a preset for my workflow, so I don't choose processing modes each time.
Once you upload the separate tracks of two people having a conversation (i.e. podcast) it would be nice if after each file is cleaned, the system would merge the two files together into one conversation and allow for the transcription.
It would be nice to be able to rename your uploads in order to keep track.
