Used together, your audio will sound much better. So compression makes volume uniform within clips, and normalization makes it uniform between clips. This is useful for keeping a uniform volume between different clips. It takes your whole clip, and makes the loudest part 100% volume. Normalization is similar to compression and is usually the last step you’ll run. Sometimes this extra information for “loudness” is useful, like for music, but for things like voiceovers you’d want it to be fairly uniform. This is an extreme example though, and you’d never really compress your audio this much in practice. The radio edit is compressed and normalized to 100%, while the downloadable version has dips in volume levels. Take a look at this waveform of the radio edit of a Metallica song versus a downloadable version: This is actually what most songs on the radio do, referred to as the “ Loudness Wars“. Note that this does also increase background noise volume in the pauses, and on quieter parts. Here’s the same voiceover from above, but with a compressor applied: Audio compression tries to make the clip more uniform in volume. This type of compression is different from traditional digital compression, which is used to reduce file sizes. You may end up with something like the image shown above, with parts of the audio very quiet and parts very loud in a clip you’d like to be uniform.Ĭompression solves this problem. One problem you might have with your mic is how loud it is the closer you are to it.
RELATED: How to EQ and Mix Your Microphone Without Any Hardware Compression and Normalization You can EQ in Audacity as well under Effect > Equalization. Like the noise reduction, you need to select a portion of the audio to EQ, and you can preview your changes with the “Play” button. The “Vocal Enhancer” preset in Audition will probably be best. This preset cuts out the very low bass and boosts the frequencies where vocals usually exist. You can open this window under Filter and EQ > Parametric Equalizer. If you’re going for a deep radio voice, you might think you should just crank up the bass, but in fact, this will make your voice sound boomy and won’t produce the effect you want. In practice though, the art of the EQ is a lot more subtle and revolves around minor tweaks to make the audio sound good. For example, you could turn the bass up or cut it out entirely. EqualizationĮqualization, or EQing, is adjusting the volume of different pitches in the audio. From here you can set the noise profile and a few other settings.Īudacity is not as fully featured as Audition’s noise removal but will get the job done. In Audacity, just choose Effect > Noise Reduction. When doing this, try to keep the main recording out of the noise to minimize the distortion. You can also select “Output Noise Only” to preview all the noise getting removed.
You can preview the sound with the “Play” button in the bottom left corner before applying your changes. This display shows you how much noise it’s capturing at each frequency. This will open up a dialog where you can configure the reduction settings.ĭefault settings are usually fine, but you can adjust the noise floor if you’d like. Next, select “Noise Reduction (Process)” under the same menu. Select a quiet bit of audio, and select Effects > Noise Reduction > Capture Noise Print. In Audition, you’ll have to first capture a noise print before you can use the noise reduction. There are a lot of other effects, like hiss remover, that you can use to mitigate different frequencies, and adaptive noise reduction, which doesn’t need a noise print. You can perform noise reduction in a lot of different ways, but one of the best ones uses something called a noise print to selectively cut out noise, and is useful for all kinds of noise. Looking closer, these lines of noise stretch across all of the audio.Īfter noise reduction, there’s still noise, but there’s much less of it.īecause it cuts out those frequencies, this does distort the audio a little bit, which is where having a less noisy microphone comes in handy, as you can only do this so much without it sounding like you’re talking through a tin can. Before noise reduction, you can see here at the end of the audio (while I wasn’t talking) there’s still a lot of data. It shows levels of noise at each frequency, over time. The spectral frequency display in Audition is useful for visualizing noise.