Stability AI updates its free text-to-song instrument: 3 new options


Stability Audio, a text-to-music AI instrument from Stability AI, as soon as reached a most of 90 seconds. Now, you may create longer audio content material.

Stability AI introduced Steady Audio 2.0, an replace to Steady Audio 1.0 that lets customers generate AI sounds for as much as three minutes.

See additionally:

StableLM: What to learn about Stability AI's language mannequin

What's new in Static Audio 2.0?

As talked about, Stability AI has launched Steady Audio 2.0, an AI audio generator with a free tier. The brand new mannequin comes with the next new options:

  • With textual content prompts, customers can generate high-quality, full tracks with “coherent musical construction” for as much as three minutes at 44.1 kHz stereo.

  • Along with text-to-audio, Stability Audio 2.0 now has text-to-audio capabilities. In different phrases, you may convert uploaded audio samples by pure language indicators

  • Stability AI expanded the sound-effect technology of Steady Audio, permitting artists and composers better “flexibility” and “management”.

Steady Audio 2.0 was educated on a licensed dataset completely obtained from the AudioSparks music library. In accordance with Stability AI, opt-out requests from composers and artists are revered, making certain that creators are pretty compensated.

Along with the free tier of Steady Audio 2.0, there are additionally premium subscriptions that supply entry to creator licenses and bigger month-to-month allowances for monitor technology.

synthetic intelligence

Leave a Comment