Forge is available: build a website with AI from your RodiumAi account.

Try Forge
MiniMax

MiniMax Music Cover

Healthyaudiospeech
Context
-
Max output
-
Speed
Fast
Quality
Basic
Released
2026-04-10
Input: / Output:
AudioAudio

About this model

Audio-to-audio song transformation that preserves melody while changing style. MiniMax Music Cover is MiniMax's song-to-song transformation model for reimagining an existing track in a new style.

Pricing

RateRODIUSD (ref.)Unit
Per unit
Per generation113.7~ 0.15per generation (RODI/gen, USD/gen)

RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.

Providers & pricing

ProviderInputOutputCachedFree tierStatus
Runware

Runware

Default

All rates (1)
  • Per generation113.7 RODI/gen
----No data

Capabilities

Streaming
Tool calling
Vision
JSON mode
Reasoning

API usage

Examples

…

Example response

…

With new lyrics

…

Use cases

  • Re-record a song in a new style or with another voice, keeping its melody.
  • Produce demo versions of a track for a client or an artist.
  • Turn a hummed or recorded idea into a produced piece.
  • Create a licensed-free alternative arrangement of your own songs.

Notes

  • This model re-sings an existing track, so the source audio is required. Pass it as runware.inputs.audio (an https:// URL the service can fetch). It must last between 6 seconds and 6 minutes.
  • Do not send duration: the length of the cover follows the source audio.
  • prompt is required and must be 10 to 300 characters. It describes the new style.
  • Optional lyrics (10 to 1000 characters, with tags such as [Verse], [Chorus]), seed (0 to 1000000), and output_format (mp3, wav, flac or ogg).
  • Only upload audio you own or have the right to adapt.
  • Use a long client timeout (600 s) and do not retry on timeout: a retry starts and bills a second generation.
View all