AI Blocks › Build and ship software
Text to music maker
Describe the music or sound you want. Get a generated clip, even one that follows a melody you give.
Text to music maker is a free AI skill for the job "Build and ship software". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by Orchestra Research · Thinking: low
Made by Orchestra Research. See the original on GitHub; we copied it as it is, with its licence.
What it does
Type what you want to hear, such as "calm piano with soft rain", and get an audio clip back. You can also hum or supply a melody and have the new music follow it, or ask for a sound effect like footsteps on gravel. The skill uses Meta's AudioCraft library in Python. MusicGen makes music from text, with optional melody guidance and stereo output. AudioGen makes sound effects. It helps you choose a model size, set clip length and creativity settings, and write prompts that name genre, mood and instruments. You need Python and a computer with a graphics card for decent speed.
You give it
- A text description of the sound
- A melody file (optional)
- Clip length
- A computer with Python and a graphics card
You get
- Generated audio clips
- A prompt that names mood, genre and instruments
- Model size advice
- Code you can rerun with changes
Use it when
- You need background music for a video and have no budget for stock tracks.
- You want a short sound effect for a game or demo.
- You have a tune and want it rendered in a different style.
- You are testing audio ideas before a producer gets involved.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run Python code on a computer with a GPU.