MiniMax Music makes full songs with vocals. Describe the style, write the lyrics and get a sung track ready for the timeline.
MiniMax Music generates complete songs, instrumentation and sung vocals, from two inputs: a style prompt (“warm indie pop, female vocal, 90 bpm”) and your lyrics. It is the fastest route from an idea to a custom soundtrack.
Generated tracks are saved to your Assets as audio clips. Drop one on an audio lane, trim it to the cut, and ducking keeps it under any voiceover automatically.
At a glance
Type: Music with vocals
Inputs: Style prompt + lyrics
Output: Full mixed track
Pricing: Flat per generation
What it is best at
Sung vocals from your lyrics
Style control through a plain-language prompt
Flat price per song, cheap enough to iterate
What it costs
From 6 tokens ($0.06) per track.
Settings
Tokens
Price
Per track
6
$0.06
Prices come from the live catalog at $0.0100 per token, the pay-as-you-go rate; subscriptions include tokens at a lower rate. The exact price is shown before you generate, and a failed generation is refunded.
Questions
Can I write my own lyrics for MiniMax Music?
Yes, lyrics are a dedicated input. Hiroska’s AI chat can also draft lyrics for you and send them into the generation.
Can I use MiniMax Music tracks in published videos?
Generated tracks are yours to use in your exports. As with all generative music, avoid prompting for a specific existing artist’s sound-alike in commercial work.
How does MiniMax Music fit the video workflow?
Tracks drop onto stacked audio lanes. Automatic ducking dips the music under voiceover, and clip-level volume and fades finish the mix.