Adobe's latest web-based audio editing tool is ready to be used by users looking to improve the sound quality of audio recordings.
Enhance Speech promises to clean up audio recordings with the magic of AI.
The tool started as part of the Shasta project, which has since evolved into Adobe Podcast, an online space for AI-powered audio recording and editing. And since the company focuses on a broad podcasting scene, speech enhancement is as accessible as possible.
Update on the fly
Enhance Speech works online and is free to use in beta. Users may lose granular control of an entire digital audio workstation, even though it probably depends on some of the technologies found in Adobe Audition.
Users upload a file: Currently only MP3 and Wav are supported, with a limit of 1 hour and 1 GB. After processing, they can play, upload, or enhance another file. The toggle switch is a particularly nice addition. Allows users to hear the audio before and after the enhancement during playback.
TechRadar Pro ran some speech files through Enhance Speech. Overall, the results were good, as long as you're not looking for a broadcast-quality clean. Distant voices felt closer to the mic rather than just louder. Background noise has been significantly reduced. However, muffled speech can sometimes sound tinny when the system overcorrects. Expect more, but not the best.
User reviews (opens in a new tab) have also been mixed. Many liked what they heard, but some were less impressed and reported ghost voices among other issues. Whether Enhance Speech lives up to Adobe's claim that "vocal recordings sound like they were recorded in a professional studio" is debatable.
But as Adobe continues to put AI into its tool stack, it's interesting to see how this technology is applied to flagship apps like Photoshop and Premiere Pro and smaller-scale tools like it and Project.Blink, a hybrid video editor and image processor. texts.
Try Adobe's Enhance Speech here (opens in a new tab).