Stable Audio

Model

Stability AI's API for generating music and sound effects from text

Price: Free credits, then paid
Access: API key

About

Stable Audio is Stability AI's audio model API. It generates music and sound effects from text, or reworks an audio sample, as 44.1 kHz stereo. Stable Audio 3.0 makes tracks up to six minutes long for 26 credits ($0.26) per generation.

What you can do with it

Generate music tracks from a text description of genre, mood and instruments
Create sound effects for games, videos and apps from a prompt
Transform an existing audio sample or inpaint part of a track

Get started

Sign up at platform.stability.ai (Google sign-up gets 25 free credits)
Create an API key on the API Keys page

Example

curl -f -sS "https://api.stability.ai/v2beta/audio/stable-audio-2/text-to-audio" \
  -H "authorization: Bearer $STABILITY_API_KEY" \
  -H "accept: audio/*" \
  -F prompt="Cheerful acoustic guitar with live drums and rhythmic claps, happy and uplifting" \
  -F output_format="mp3" \
  -F duration="20" \
  -F model="stable-audio-2.5" \
  -o "./output.mp3"

Details

Hosting: Hosted service
Available in: Worldwide
MCP server: None