ElevenLabs is one of the most prominent and best generative artificial intelligence sound platforms available, creating synthetic and cloned audio from small samples

Now expanding into the field of sound effects, creators can generate a variety of noises from simple prompts that can be used in presentations, movies, and podcasts

I have tried this tool and it can create complex, multi-layered sound effects from relatively simple prompts, such as animal, atmospheric, and technical noises

It still wasn't perfect, struggled with certain noises, and didn't quite get that mid-90s modern sound

Like other generative AI tools, ElevenLabs' sound effects model was trained on a huge amount of data, including record sounds of real-world objects

Each object, animal, or scene used in the training dataset was well labeled and described so that the AI could learn to replicate the noise

To use this tool, there is a standard text box familiar to anyone who has used more or less any generative AI tool, and a button to generate

ElevenLabs' sound effects generator generates five sounds from the same prompt

It seems to be particularly good at weather sounds and sounds of nature, including animals, but not electronic sounds

I gave it seven prompts to see how well it could handle a variety of sounds These included the crackling of a campfire, ocean waves, a thunderstorm, wind chimes, and an old-fashioned train whistle

Overall, it worked well with most of the prompts, but of the five versions generated in response to a prompt, only one or two usually worked well for longer than a few seconds

The tool is also built to double up on sound In the video of the waves crashing on the beach, we needed two sounds: the sound of the waves and the sound of the seagulls

Sound is a rapidly growing field in AI, from music tools to synthetic voices and now sound effects and custom noises Sound adds a new dimension to generated video, gives slides a new form of storytelling, and makes the creation of podcasts more immersive