ElevenLabs, which uses AI tools to create and edit synthetic voices, previews an AI model that can generate lyrics and samples of songs from text prompts
and you have to hear these clips to appreciate it Maximilian Schreiner / The Decoder : ElevenLabs unveils new AI music generator ‘ElevenLabs Music’ Daniel Croft / Cyber Daily : OpenAI developing AI-generated image detector X: @elevenlabsio : Here's an early preview of ElevenLabs Music. All of the songs in this thread were generated from a single text prompt with no edits. Title: It Started to Sing Style: “Pop pop-rock, country, top charts song.” [video] Ammaar Reshi / @ammaar : Our music model @elevenlabsio is coming together! Here's a very early preview. 🎶 Have your own song ideas? Reply with a prompt and some lyrics and I'll generate some for you! [video] Bryan / @bryancsk : Discussed this stuff with an opera-trained singer yesterday and her insight was a lot of the articulation from Suno et al. is based on speech, not song. This is why it sounds a bit auto-tuned, it's modulating speech to a pitch, not fully expressing sung words qua song. Carles Reina / @carles_reina : Sneak peek into the future @somewheresy : ok so given these are all diffusion models but where tf are people licensing this data Luke Harries / @lukeharries_ : First speech, then SFX. What's next... music? Victor Swift / @victorswift : This is as good as music on the radio As musicians, I think this is a wakeup call that we need to put out better music Push the envelope Embrace unique soundscapes and our unique voices Robert Scoble / @scobleizer : Hey AI can you compare to the other music generators, like @suno_ai_ or @udiomusic and tell me how it compares? Also, I have a list of 106 AI companies doing music stuff. This just got added: https://twitter.com/... See also Mediagazer