How to use AI in audio Asbjoern Andersen


What does AI mean for us in sound? Many are understandably worried that it might take our jobs away, but in this Sound Opinions piece, sound designer and recordist Ana Monte argues that AI offers plenty of ways we can use it creatively - without making ourselves redundant:
By Ana Monte, with additional research by Wieland Müller
Please share:
Animal Hyperrealism IV Is Here!

AI is not here to replace us. It’s a powerful tool that, when placed in the right hands, unlocks new creative possibilities

As a sound designer, I’ve been fascinated by the growing role AI is playing in the world of audio.
But here’s my 2 cents: AI is not here to replace us. It’s a powerful tool that, when placed in the right hands, unlocks new creative possibilities.

AI can assist in a variety of ways:

 

Restoring damaged audio: AI can remove clicks, hums, and background noise automatically, saving you time on tedious manual fixes. (Examples of tools to explore: Accentize dxRevive, Supertone, iZotope RX)

Generating sound sketches: AI can create sketches based on prompts, giving you a quick starting point for sound design. (Examples of tools to explore: Krotos Studio Pro, Sonic Alchemist)

Smart EQ adjustments: AI can analyze your audio and suggest custom EQ settings, streamlining the mix process. (Examples of tools to explore: Soundtheory Gulfoss, Sonible Smart: EQ 3, Oeksound Bloom)

Editing audio through text: AI lets you edit audio by editing text, making dialogue editing faster. (Examples of tools to explore: Descript, Spext)

Finding similar sounds: AI can analyze your sound library and help you discover similar sounds quickly, saving time on browsing (Examples of tools to explore: Sononym, Waves COSMOS Sample Finder)

Isolating stems from a mix: AI can separate individual stems from a full mix, allowing you to extract elements for remixing or editing. (Examples of tools to explore: audioshake.ai, Audionamix ADX TRAX, LALAL.AI)

– Simulating reverb environments: AI can recreate realistic reverb spaces, allowing you to apply different acoustic environments to your audio without complex manual adjustments. (Examples of tools to explore: Accentize Chameleon, Zynaptiq Adaptiverb)

– Processing voice recordings: AI can process voice recordings, refining clarity, adjusting tone, and improving intelligibility in real-time. It can also adapt to different voice profiles, creating personalized audio outputs. (Examples of tools to explore: Auphonic, SoundID VoiceAI, Supertone Shift)

But here’s the thing, AI doesn’t have the creative intuition or understanding of human emotion that we, as sound engineers and sound designers, bring to every project (for writing, editors have seen this as well). It’s our artistry, vision, and expertise that guide these tools to produce something special.

Let’s embrace these technologies, not fear them! This way we can focus on what really matters: creativity, storytelling, and emotional impact. If you have suggestions for AI audio tools that empower us, be sure to share them in the comments!

About Ana Monte:

Ana Monte, co-founder and sound designer at DELTA Soundworks, is a leading expert in spatial audio. She specialises in creating immersive content for Fulldome, XR, and Themed Attractions. Learn more about her here

 

Please share this:


 



 
 
THE WORLD’S EASIEST WAY TO GET INDEPENDENT SOUND EFFECTS:
 
A Sound Effect gives you easy access to an absolutely huge sound effects catalog from a myriad of independent sound creators, all covered by one license agreement - a few highlights:

  • Strident and Demonic

    Expand the timbre of your horror violins and cellos with CIRCUS, a sinister sample pack featuring 180 WAV sounds of screeching or high-pitched string noises, perfect for horror music and dark sound design.

    Creative Tension

    This collection offers a curated selection of screeches, high-tension tremolo, heavy jeté strokes, dark demonic textures, finger patterns, chaotic string elements, clock loops and bow accents.

    Haunting and Experimental

    Create haunting atmospheres, perfect for horror, thriller or experimental soundtracks. Every element has been designed to unsettle and disturb, blurring the line between music and noise.

  • ⏰ For a very limited time:
    Add this library to the cart and enter ah4launch in the cart coupon field – to sprinkle an extra launch discount, on top of the current discount!

    Animal Hyperrealism Vol IV is a sound library containing animal vocalisations, from real to designed creatures totaling more than 2000 individual sounds in 294 files. The sounds were recorded in zoos, and wildlife centers.

    The asset list includes but is not limited to: hippos, hyenas, vultures, dwarf mongooses, elephants, African cranes, parrots, tigers, pigmy hippos, rhea ostriches, brown bears, pheasants, wildebeests, African wild dogs and many more. The content has been recorded at 192KHz with a Sanken CO100K, an Avisoft CMPA and a Sennheiser 8050 for center plus two Sennheiser MKH8040 for stereo image.

    The resulting ultrasonic spectrum is rich and allows for truly extreme manipulation of the content.

    15 %
    OFF
  • a collection of female orgasms performed by eight professional voice actors, including the voices of orgasm, moans and oral sex, breathe life into your female characters by giving them high-quality voices with this newly updated audio library!

    this collection features 65 professionally recorded human sounds, created by various voice over artists and actors.

    80 %
    OFF
    Ends 1761951599
Explore the full, unique collection here

Latest sound effects libraries:
 
  • Car Sound Effects Compact Cars 3 Play Track 2385 sounds included, 412 mins total $250

    Compilation of 10 different compact cars. Sounds are recorded with RØDE NTG1, RØDELink Lav, Line Audio Omni1, Shure KSM137, Shure VP88, Sonorous Objects SO.3 FEL Pluggy XLR EM272 and FEL Clippy XLR EM272 microphones, Sound Devices MixPre-6 II, Zoom F3 recorders. Library contains wav files of driving, interior and exterior foley, mechanical and electrical sounds.

  • All files are recorded 32bit, 192 kHz, with RØDE NTG1, Line Audio Omni1 and FEL Clippy XLR EM272 microphones, Sound Devices MixPre-6 II recorder. Library contains wav files of driving, interior and exterior foley, mechanical and electrical sounds. It is only available in UCS.

  • Hum, Buzz & Glitch Sound Effects Massive Soldering Play Track 426 sounds included, 15 mins total $29.99

    MASSIVE SOLDERING – 426 files of solder sound effects, from several component repair sessions. From quick zips and zaps, to burning, sizzling and melting sears. Massive Soldering comes in at over 15 minutes, of metallic hisses and harsh bubbling. Bring the power of metallic vapors to your next project. Recorded at 192kHz and 32bit, using microphones capable of recording ultrasonic frequencies. Massive Soldering filenames are in the Universal Category System format with additional Metadata baked-in.
    Don’t need a Massive amount of Solder sound effects? We offer ‘Mini’ sound effect libraries as companions for all of our ‘Massive’ sound effect libraries. All recordings are unique to each library with no overlap. Go Mini today, and upgrade to the corresponding Massive library later, when you need more of that particular sound effect.

    40 %
    OFF
  • Hum, Buzz & Glitch Sound Effects Mini Soldering Play Track 50 sounds included, 2 mins total $6.99

    MINI SOLDERING – 50 files of solder sound effects, from several component repair sessions. From quick zips and zaps, to burning, sizzling and melting sears. Mini Soldering comes in at over 2 minutes, of metallic hisses and harsh bubbling. Bring the power of metallic vapors to your next project. Recorded at 192kHz and 32bit, using microphones capable of recording ultrasonic frequencies. Mini Soldering filenames are in the Universal Category System format with additional Metadata baked-in.
    Looking for a Massive amount of Solder sound effects? We offer ‘Massive’ sound effect libraries as companions for all of our ‘Mini’ sound effect libraries. All recordings are unique to each library with no overlap. Go Mini today, and upgrade to the corresponding Massive library later, when you need more of that particular sound effect.

    30 %
    OFF
  • Foley Sound Effects Cards and Dice Play Track 930+ sounds included $14.99

    Cards and Dice is a winning collection of tactile tabletop sounds. Shuffle, riffle, deal, flip and fold through two distinct decks — one old and soft, one crisp and snappy.

    Roll D20s, D6s and mini D6s by hand or with a dice tumbler across felt, wood and cork tabletops.

    Stack, slide and scatter poker chips with satisfying weight and precision.

    Perfect for games, animations and interface feedback.

    Includes 930 files recorded in 24bit / 96khz.

    25 %
    OFF

   

Leave a Reply

Your email address will not be published. Required fields are marked *

HTML tags are not allowed.