ElevenLabs Unveils Impressive AI Music Generator with Realistic Vocals

ElevenLabs Unveils Impressive AI Music Generator with Realistic Vocals

ElevenLabs, known for its natural-sounding AI voices and accurate voice cloning, has shared an early preview of its upcoming text-to-music product, ElevenLabs Music. The tool can create full-length songs with realistic vocals from a single text prompt. And, based on the examples we have heard, this could be a gamechanger—it certainly has our attention.

Here are some examples that were share by ElevenLabs on X, take a listen and judge for yourself. Notably, all of the songs shared were generated from a single text prompt with no edits.

Title: It Started to Sing
Style: Pop pop-rock, country, top charts song.
Title: My Love
Style: "Indie Rock with 90s influences, featuring a combination of clean and distorted guitars, driving drum beats, and a prominent bassline, with a moderate tempo around 120 BPM, and a mix of introspective and uplifting moods, evoking a sense of nostalgia and hope."

The samples shared by ElevenLabs staff showcase the tool's versatility across various genres, including jazz, pop, dubstep, and country.

Title: It Started to Sing (Jazz)
Style: A jazz pop top charts song with emotional vocals, catchy chorus, and trumpet solos.
Title: Broke My Heart
Style: "Smooth Contemporary R&B with subtle Electronic elements, featuring a pulsing 104 BPM drum machine beat, filtered synths, lush electric piano, and soaring strings, with an intimate mood."

The things that jump out immediately for me are:

  1. The ability to generate fully mastered tracks up to three minutes from a single prompt. This is something you can't do in Udio and Suno without the need for edits or extensions.
  2. How are lyrics being generated? Above you can listen to a jazz version of "It Started to Sing". This suggests that the tool likely handles the "style" prompt separately from the lyrics generation.
  3. Surprisingly, you can generate NSFW music with profanity. Other platforms block curse words (in English at least).
Warning: NSFW Content! The music above contains profanity

The tool is still in development, and for now, ElevenLabs is limiting access to employees. We're looking forward to getting our hands on it and doing a deeper dive.

The AI music landscape has been evolving rapidly, with recent advancements like the first Suno track that surpassed over a million listens, and Udio's hyper-realistic vocals. ElevenLabs Music could raise the bar even higher.

While AI music generation continues to be a hotly debated topic with issues around copyright and the potential impact on artists' livelihoods, it also presents opportunities for creative expression. ElevenLabs has also invested in products like its Voice Library marketplace, that launched in January, which allows users to sell their AI-cloned voices while maintaining control over availability and compensation.

ElevenLabs Music has the potential to be a game-changer. With its ability to generate full-length, high-quality tracks from a single prompt, it could democratize music creation and open up new avenues for creative expression. As the product moves from preview to launch, it will be interesting to see how musicians, the industry, enthusiasts, and society as whole respond.

Chris McKay is the founder and chief editor of Maginative. His thought leadership in AI literacy and strategic AI adoption has been recognized by top academic institutions, media, and global brands.

Let’s stay in touch. Get the latest AI news from Maginative in your inbox.

Subscribe