ElevenLabs AI generator generates explosions or other sound effects with one click

ElevenLabs already offers AI-generated versions of human voices and music. Now he will allow it people create sound effects for podcasts, videos and games. Novel Sound Effects tool can generate up to 22 seconds of audio based on user prompts, which can be connected to the company’s voice and music platform, and provides users with at least four downloadable audio clip options.

The company says it worked with stock media platform Shutterstock to create a library and train its model based on audio clips. Shutterstock has licensed its content libraries to a number of AI companies, including OpenAI, Meta and Google.

Sound Effects is free to operate, but paid tiers can operate generated audio clips with commercial licenses, while free users ‘must attribute ElevenLabs by including “elevenlabs.io” in the title. ElevenLabs users have a set character limit when writing prompts, with free users receiving 10,000 characters per month. For audio effects, ElevenLabs states on its FAQ page that an allocation of 40 characters per second will be required if users set the duration of the audio clip themselves. If you operate the default audio duration, you will be charged for 200 characters per prompt request.

There are already libraries of clips with sound effects on the market intended for creators, filmmakers and video game developers. But sometimes they can be pricey or cause problems in getting the right kind of sound. ElevenLabs says in its blog post that it designed Sound Effects “to generate rich and immersive soundscapes quickly, inexpensively, and at scale.”

Other AI developers are also developing their own text-to-audio generators. Last year, Stability AI released Stable Audio, which creates audio clips with music and sound effects, and Meta AudioCraft models generate natural sound (e.g. background noises such as wind or traffic).