Today, I’m testing out a revolutionary AI audio editing software from Adobe. Earlier at my shoot, my buddy, Yokani, sent me a text with examples of him editing audio from interviews and a wedding ceremony, and my mind was blown. I had to find out more about it and try it for myself.
I asked my client to say a few lines for me. Normally, I use a Rode VideoMic Pro, so I had him record with both the on-camera microphone and the Rode mic. My goal was to compare how the original audio stacks up against the AI-enhanced audio.
I imported the recordings into Adobe Premiere to create a sequence named “AI Test”. I then adjusted the gain to ensure that the audio levels were appropriate:
Hello there, this should be the new AI generated audio.
Next, I rendered the clip as an MP3 file. The software accepts MP3 and WAV formats, so I chose MP3 for convenience.
The software we’re exploring is called Enhanced Speech by Adobe, formerly known as Project Shasta. It essentially creates a new, improved version of your voice based on your input.
I uploaded the MP3 file to the Enhanced Speech platform. It took around 20 seconds to process.
I downloaded the transformed audio file and compared it with the original:
Original Audio:
Hello there, this should be the new AI generated audio.
AI-Enhanced Audio:
Hello there, this should be the new AI generated audio.
The difference was astonishing. The AI version sounded significantly better than anything I could achieve with traditional audio editing techniques.
The Enhanced Speech software by Adobe is a game-changer. It leverages AI to produce studio-quality audio, potentially eliminating the need for manual audio editing. While it's not perfect—for instance, it struggles with distant recordings where the AI can't decipher the words—it still represents a monumental leap forward in audio technology.
Q: What is Adobe's Enhanced Speech? A: It's an AI-powered audio editing software that improves audio quality by creating an enhanced version of your voice based on the input file.
Q: What formats does Adobe Enhanced Speech accept? A: It accepts MP3 and WAV files.
Q: How long does it take to process audio? A: The processing time is relatively short, usually around 20 seconds.
Q: Is it always accurate? A: While the AI does a fantastic job with clear and direct recordings, it struggles with distant recordings where the audio is faint or unclear.
Q: Can this software replace traditional audio editing? A: Although it handles many tasks exceptionally well, it might not entirely replace traditional audio editing, especially in complex scenarios. However, it can significantly reduce the workload.
In addition to the incredible tools mentioned above, for those looking to elevate their video creation process even further, Topview.ai stands out as a revolutionary online AI video editor.
TopView.ai provides two powerful tools to help you make ads video in one click.
Materials to Video: you can upload your raw footage or pictures, TopView.ai will edit video based on media you uploaded for you.
Link to Video: you can paste an E-Commerce product link, TopView.ai will generate a video for you.