We’re excited to announce that we updated our filler sound detection model in Resound to be even more accurate and less work for you.
Filler sound detection v0.5.1 greatly reduces the number of incorrect edits. That means you should have less edits to review, and less edits marked Keep. You’ll also notice more accurate edit boundaries (start and end times).
See how it works on your voice today!
Editing your podcast in Resound is about getting your time back. But one friction point we discovered recently was that you had to chase the cut/keep button around when you were editing, which caused some annoyance and took more time.
Now the review button sits in the middle of the editor and doesn’t move. It’s a small change but a big improvement.
But that’s not all. We’ve taken a lot more of your feedback into account. So let’s dive into what’s new in Resound:
🔐 Password requirements now get checked off as you type.
No more guessing if your password is strong enough. As you type the requirements will be checked off one-by-one.
✅ See your last export time and number of tracks.
Hover over the green checkmark in the project list to see the last time you exported a project. You’ll also see how many tracks are in a project in the project list and the editor window.
💰 Introducing our private affiliate program.
We’re alpha testing an affiliate program that is by application only. Reach out if you think you’d like to share Resound with your audience to make money.
🩹 Last but not least, we fixed some paper cuts.
We fixed a lot of little bugs and made some subtle improvements to the app. For example, we got rid of the “restore” edit state so you simply choose between “cut” or “keep” each time you review an edit.
We heard a lot of feedback that the editing terms “Accept” and “Ignore” in Resound were confusing. We totally agree, so we just rolled out a new change to fix this issue.
✂️ Cut and Keep are the new terms used in the editor instead of Accept and Ignore.
🟥 ”Cut” means this audio will be deleted
🟩 ”Keep” means this audio will be left alone
🟦 A blue edit means it's unreviewed
Filler Sound Detection v0.4 improves the accuracy of filler sounds detected (e.g. umm) while also reducing the number of filler words (e.g. you know) detected. This subtle change sets Resound up to give you even more fine-tuned control over your edits in the near future. Try uploading an audio file with v0.4 to see how well it detects filler sounds in your voice.
Resound’s free public beta has come to a close and four new subscription plans have been launched. You can use Resound to edit 1 hour of audio each month for free, then upgrade to one of our three paid plans to unlock additional processing time, multitrack editing, and longer project storage. Learn more here.
Version 0.2.0 introduced breath detection to the app as a byproduct of how we built it. We heard from users like you that these breaths were more of a distraction than a value-add, so we removed them. Now you can upload audio and enjoy the same overall performance of filler sound detection without the distraction of reviewing breaths.
Drag and drop files directly into the upload circle in the app. Hold down shift to select up to 4 files at the same time. You can also click the “upload” button to manually select files.
Anyone can create a free account during this limited-time beta. We’re quietly launching the public beta with a redesigned marketing site.
You can now switch between All Speaker track view or Individual audio track view on multitrack episodes. All Speaker track view is shown by default but you can toggle your view by selecting the Track: All Speakers button in the top right corner. Edits made on single-track view will be applied to both tracks so that tracks are kept in sync.
You can now export AAFs on multitrack episodes up to 4 tracks.
The editor takes some time to load a full waveform for the average podcast, so we added a visual load icon so you can see the progress while you wait for the editor to fully render.
Resound is live for early waitlist users. We’re progressively letting everyone in over the coming weeks.
Upload, edit, and export up to 4 tracks. We’ll keep all the edits in sync on the backend for you, making cuts in both tracks.
We’ve refactored our entire tech stack. This ML model increases the accuracy of the boundaries in each edit, recognizes distracting breath sounds, and makes predictions in seconds rather than minutes.
The first work in progress version of the app is now online after several months of writing code and setting up infrastructure.
If you haven’t noticed yet, Resound’s brand has been highly influenced by the discovery of Chladni figures - the visualization of sound in sand.