ElevenLabs has launched its text-to-sound generator Sound Effects for all users, available now at the company’s website. The new AI tool can create audio effects, short instrumental tracks, soundscapes and even character voices. Sound Effects “has been designed to help creators — including film and television studios, video game developers, and social media content creators — generate rich and immersive soundscapes quickly, affordably and at scale,” according to the startup, which developed the tool in partnership with Shutterstock, using its library of licensed audio tracks.

VentureBeat describes Sound Effects as a potential game-changer for creators who either couldn’t find the free sound they were looking for or didn’t have the budget to record or license a new sound — the options typically available. “ElevenLabs’ new Sound Effects tool changes that, giving creators and production teams a way to get exactly what they want by simply typing it in plain, conversational English,” VentureBeat writes.

ElevenLabs says user text prompts describing the sound they’re after will generate up to six distinct audio samples from which to select. Users can then download their choice or store it on the ElevenLabs’ website.

VentureBeat tested the tech and was able to produce “clear outputs in about 30-40 seconds,” including “a range of audio samples, covering standard ambient noises such as thunderstorms, doorbells and coins jingling to more complex ones like monkeys chattering, cars racing, people eating at a diner or a train coming to a halt.”

ElevenLabs CEO Mati Staniszewski told VentureBeat the new tool “can generate instrumental music tracks up to 22 seconds with prompts like guitar loop, jazz saxophone solo, and music techno loop,” and “can also create a variety of character voices using prompts like woman singing dancing in the sand, we watched the daylight end or an ogre saying ‘stay away puny human.’”

ZDNet says the AI Sound Effects tool is available in “different tiered plans to accommodate user needs,” noting “you can try the tool for free, although it does count towards your monthly 10,000-character limit.”

Shutterstock Chief Enterprise Officer Aimee Egan noted in the ElevenLabs announcement that the audio used to train  the Sounds Effects audio model is “ethically-sourced.”

ElevenLabs created a splash earlier this year when it teased Sound Effects by adding its audio to imagery produced by OpenAI’s Sora. Pika Labs subsequently used the ElevenLabs tech to create its own Lip Sync tool.