Start voice cloning Eleven Labs was introduced a new tool for users to create sound effects via prompts today. Company first announced the project in February.
The tool, which is available to all users starting today, lets users type in prompts such as “waves crashing,” “metal jingle,” “birds chirping,” and “racing engine” to generate snippets of sounds.
The sound effects tool can also create instrumental music clips up to 22 seconds long with prompts such as guitar loops, jazz sax solos and techno music loops.
Free users get 10,000 character generations per month — an audio byte generation requires about 150 characters per request. Essentially, free level users can create almost 60 sound effects per month. They must also attribute the audio to “elevenlabs.io” in the title while posting any content containing the audio clip.
ElevenLabs said it used Shutterstock’s audio library of licensed tracks as a tool to train its model. The company added that users who tested the tool during the alpha testing phase included video game developers, film producers, social media content creators and marketers.
The startup noted that the tool does not allow audio generation through messages that violate it Prohibited Content and Use Policywhich includes topics such as self-harm, threats to children’s safety and fraud.
While there are only a handful of companies and startups working on AI-powered audio, ElevenLabs may find the music production space crowded. Harmonai powered by Stability AI released Dance Diffusion. Google has worked on MusicLM. OpenAI has a Jukebox. and Meta has AudioCraft’s model. TikTok and Adobe have also experimented with their own AI-based music creation tools.
We’re launching an AI newsletter! Sign up here to start receiving it in your inbox on June 5th.
Arabic
Chinese (Simplified)
Dutch
English
French
German
Italian
Portuguese
Russian
Spanish