Secure Audio, a text-to-music AI device from Stability AI, as soon as maxed out at 90 seconds. Now, you may generate longer audio content material.
Stability AI introduced Secure Audio 2.0, an replace to Secure Audio 1.0 that lets customers generate as much as three minutes of AI sound.
StableLM: What to learn about Stability AI’s language mannequin
What’s new with Secure Audio 2.0?
As talked about, Stability AI launched Secure Audio 2.0, an AI audio generator with a free tier. The brand new mannequin comes with the next new perks:
-
With textual content prompts, customers can generate high-quality, full tracks with “coherent musical construction” for as much as three minutes lengthy at 44.1 kHz stereo
-
Along with text-to-audio, Stability Audio 2.0 now has audio-to-audio capabilities. In different phrases, you may remodel uploaded audio samples through pure language prompts
-
Stability AI expanded Secure Audio’s sound-effect technology, permitting artists and musicians extra “flexibility” and “management”
Secure Audio 2.0 was solely skilled on a licensed dataset sourced from AudioSparx music library. Decide-out requests from musicians and artists are honored, based on Stability AI, guaranteeing creators are pretty compensated.
Along with a Secure Audio 2.0’s free tier, there are additionally premium subscriptions that provide entry to creator licenses and larger month-to-month allowances for observe technology.
Subjects
Synthetic Intelligence
