Stable Audio 3 Medium2026ai_remix

Neural Remix - Stable Audio 3 - Stable Audio 3 Medium

Model card for the Stable Audio 3 Medium restoration preset in Neural Analog (Stable Audio 3 Medium, 2026)

Available in Studio. Uses standard processing minutes. Maximum input length is 6 minutes.

Stable Audio 3 Medium Description

Recreates the track with Stability AI's Stable Audio 3 Medium audio-to-audio editing model. This prompt-guided remix mode uses the source audio as a reference while the text prompt steers style, tone, and instrumentation. Recommended for: creative remixes, inpainting missing musical ideas, alternate takes, and low-end or texture repair that benefits from generative reconstruction. Try a short section first for predictable results.

Stable Audio 3 Medium Architecture

Stable Audio 3 Medium Parameters

KeyLabelOptionsDescription
strengthRemix Strength0.01 - Minimal edit (0.01), 0.1 - Light edit (0.1), 0.5 - Balanced edit (0.5), 0.6 - Moderate remix (0.6), 0.75 - Strong remix (0.75), 0.95 - Totally different song (0.95)How much Stable Audio 3 can reinterpret the source. Higher values let the model rewrite more of the original recording.
promptPromptFree textDescribe the target sound, style, instrumentation, tempo, and production character Stable Audio 3 should create from the source audio.
prompt_strengthPrompt Strength0.5 - Less prompt strength (0.5), 1 - Base prompt strength (1), 2 - More prompt (2), 4 - Even more prompt (4), 7 - Maximum prompt (7)How strongly Stable Audio 3 follows the text prompt. Higher values amplify prompt guidance relative to the reference audio.