Stable Audio

Stable Audio is the latest AI music generation tool launched by Stability AI (the company behind Stable Diffusion), which allows users to generate original music and sound effects using AI technology through a simple web interface. Users only need to input text descriptions of the desired music and sound effects (prompts can include details such as genre, instruments, emotions, beats per minute, etc.), and audio will be automatically generated. The design of the website, the combination of colors and geometric shapes, provides a very comfortable user visual experience and experience.

How to Use Stable Audio

1. You can visit the official website of Stable Audio at stableaudio.com to play the sample music provided or click “Try it out” to start generating.
2. Then register/log in to your account (you can log in using your email or Google account). After a successful login, you will be redirected to the generation interface in the backend.
3. Enter prompts and descriptions in the text prompt input box. You can also adjust the length of the generated music at duration.
4. Finally, click the circular black arrow button to generate music. After the generation is complete, you can play and download it on the right side.

The price of Stable Audio

Stable Audio offers both free and paid subscription plans, both of which support text prompts that describe music genres, instruments, moods, rhythms, and other parameters.

• The free version allows users to generate 20 audio clips of up to 45 seconds each per month.
•  The “Pro” paid version costs $11.99 per month. Users can generate 500 higher-quality audio clips of no more than 90 seconds each per month for commercial use.

The License of Music Generated by Stable Audio

• Free users can use the audio generated by Stable Audio as samples in your own music works (i.e., music tracks), but not for commercial purposes.
• Paid users can use it in commercial media projects: videos, games, podcasts, etc., including both internal projects and external client projects.
• Training AI models on the generated audio is not allowed.