Voice cloning startup ElevenLabs has introduced a new tool that allows users to generate sound effects and instrumental musical clips through text prompts, expanding its offerings beyond its core voice cloning technology. The tool, available to all users starting today, enables users to type in prompts such as “waves crashing,” “metal clanging,” or “guitar loops” to generate corresponding sound snippets.
The sound effects tool can generate up to 22 seconds of instrumental music clips, catering to a wide range of genres and styles, including jazz saxophone solos, techno loops, and more. This feature opens up new possibilities for various creative professionals, including video game developers, film producers, social media content creators, and marketers.
ElevenLabs has implemented a pricing model that allows free users to generate up to 10,000 characters per month, which translates to approximately 60 sound effects or music clips. However, users of the free tier must attribute the generated sounds to “elevenlabs.io” when publishing content containing these clips.
To train its model, ElevenLabs utilized Shutterstock’s audio library, which contains licensed tracks, ensuring that the generated sounds are based on legitimate sources. The company also emphasizes its commitment to responsible AI by implementing a Prohibited Content and Uses Policy, which prevents the generation of content related to self-harm, threats to child safety, fraud, and other harmful or illegal activities.
While ElevenLabs is not the only player in the AI-powered sound generation space, with companies like Stability AI’s Harmonai, Google’s MusicLM, OpenAI’s Jukebox, and Meta’s AudioCraft also exploring this field, the startup’s new tool offers a unique and accessible way for users to create sound effects and music through simple text prompts.
As the demand for AI-generated content continues to grow, ElevenLabs’ foray into sound effects and music generation positions the company as a versatile player in the generative AI space, expanding beyond its core voice cloning capabilities and catering to a broader range of creative professionals and content creators.
