Feature Requests

Perfect audio  

I have a project with about 2x 30h of audio, the 4h daily limit is slowing us down dramatically.Also the max file size of 1GB causes a lot of extra work. 

Please could there be timecodes on the transcripts. Ideally each time the speaker changes, but at the very least, at regular intervals - 2mins / 5mins / something like that. 

I use Adobe podcast for an indigenous language, but when I click “transcribe” in the editor, it says “this language is not supported for transcription”.  That’s fine, I don’t expect it to understand an endangered Native American language.  But I would like the option to upload my own transcription.  I have my own ASR model that I use so I can upload it already transcribed and I would like the option to still use Adobe Podcast for editing.  Even if it would make an attempt, then at least I could correct it myself.  But as it is it won’t let me do things like add captions to video.

Any plans on releasing Podcast enhance via API?

I am assuming this is a feature issue and not just a bug since others have reported the same thing. The exported video quality is rubbish and there are not settings available to fix this in exporting the video. It takes a well lit video and flattens it and darkens it to the point where it is too compressed to get that quality back. 

I work on podcasts that are recorded online, and take each speaker and put them through Enhance Speech.Once their audio has been processed, I have no way of finding when each guest speaks without referring to the raw files again.It would be great to have an indication of when each guest speaks, via a visible waveform within Enhance Speech, just so I don’t have to go back and check every time.This way I can quickly find when they speak, and adjust the settings to their audio :)Thanks!

por que eliminan algo que ya funcionaba, importo un audio y solo deja mejorar la voz de 0% a 100% queriendo mejorar todo en una sola barra, por que eliminan la otra opcion que te permitia mover que tanto ruido de fondo se podia eliminar o balancear, ahora todo lo hace en UNO y queda horrible

We react to videos and images on our show and need to be able to share our screens to do this. 

Please add some functionality to remove breaths. Other tools out there have this and, at least for me, Adobe Podcast would do everything I needed with the audio if it also included breath removal functionality.

A basic EQ for voice (bass, mid, treb) would be so amazing. I could go from here to shipping a video without needing editing or audio software in between. 

2-part. First, add a transcript that follows along. Second, when the transcript is edited by the user, that word is fixed in the audio. For example, if someone says "brown" but the system mishears and makes it "browth", I can find the word, correct it, and the AI will rerun that word correctly. This would have a HUGE use-case and draw untold numbers of content creators to Adobe products.

Yas

When I work in a competitor product like Descript, I can highlight or make notes in the transcript so that when I’m working on a long project (say, a podcast with 100 middle schoolers), I can run through the transcript and make a plan that’s easy to see/change. Even with more normal projects with just two speakers, being able to highlight is a necessary feature for me.

Not so much a feature request as much as a thank you for this tool! I shot an event recently that had music playing loudly on speakers, and it was audible in both the shotgun mic and lav mic and I was really concerned about how I was going to make that audio work in the edit, but there was literally nothing I could do about it on the day. Enter: fixing it in post. The Enhance Speech feature in Adobe Podcast removed the background music like it was nothing and left the voices sounding natural! I am amazed, and forever grateful! Thank you to the team who built this - keep up the excellent work!! (And higher ups, please never kill this feature, it’s a real life saver!)

Description:Adobe Podcast currently only supports English for transcription and speech recognition. I would like to request broader support for multiple languages. My personal use case is Dutch, but this need also applies to users working in other languages.Request:Dutch speech-to-text (transcription) Dutch speech recognitionWhy it matters:This would make the tool usable for a large group of professionals (e.g. education, government, media) working in Dutch and other languages, and remove the need for external tools.Expected outcome:Full Dutch support, and ideally broader multilingual support, comparable to the current English experience.

Rayhan Hassan army act saavn music chahiye dhanyvad

Bright white screens are distracting and difficult for many of us to deal with. Please let us select a dark mode when working in Adobe Podcast. Thank you!

The audio and video editing and enhancement in Adobe Podcast is great! In order to make Adobe Podcast a one-stop-shop for video/editing platform, the addition of AI generated B-roll that smartly pick the B-roll image display and duration based on the video/audio file will be superb.Imagine creating your entire content on one platform without having to switch platform and still obtain high quality production. This is what I envision with this feature. 

Premiere Pro has filler detection like “uhmm” and “aahs”. Other online editing platforms such as Descript and Riverside can also detect outtakes in addition to finding fillers. Plus, they can also filter out abrupt cuts. If Podcast can do these, it will go toe to toe with Descript and Riverside

My enterprise is unable to use the web-based Speech Enhance tool due to security policies. However, we do have licenses for Adobe Audition. Please add AI Speech Enhance to Audition. I believe it’s now integrated into Premier Pro, but this feature would be even more logical for Audition.

ণচরমযয য় মনে ত গ

I like to throw in a lot of voice overs into the queue. It’s faster if I can select all my files and download them as a zip file. 

Can you implement custom values as defaults for strength, music, bg enhancement?for example my starting point is 70/100/20

just to make my voice clear