All Models
MiniMax Music 3.0
MiniMax Music 3.0 generates complete songs with vocals and instrumentals from a prompt and lyrics.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
MiniMax Music 3.0
MiniMax Music 3.0 generates a complete song — vocals and arrangement — from a prompt and lyrics. The lyrics field is the main control. You can force an instrumental, and you can run a lyrics optimizer that reshapes phrasing to fit the melody.
Bitrates are 32, 60, 64, 128, or 256 kbps, default 256. Sample rates are 16, 24, 32, or 44.1 kHz, default 44.1. There is no duration slider and no image-conditioning slot.
Leave the lyrics optimizer off when the words are fixed — a tagline, a name, a chorus legal already approved. Turn it on when the singing matters more than the exact syllables.
What it's good for
Theme songs, vocal spots, and lyric-locked beds. If you arrived with the words already written and you need the model to sing them, that is this model. An instrumental version of the same track is available when it has to sit under narration.
Model ID
minimax/music-3.0
Output Type
Audio
Pricing
$0.15
Provider
MiniMax
Hosting
Protoface
MiniMax Music 3.0
MiniMax Music 3.0 generates a complete song — vocals and arrangement — from a prompt and lyrics. The lyrics field is the main control. You can force an instrumental, and you can run a lyrics optimizer that reshapes phrasing to fit the melody.
Bitrates are 32, 60, 64, 128, or 256 kbps, default 256. Sample rates are 16, 24, 32, or 44.1 kHz, default 44.1. There is no duration slider and no image-conditioning slot.
Leave the lyrics optimizer off when the words are fixed — a tagline, a name, a chorus legal already approved. Turn it on when the singing matters more than the exact syllables.
What it's good for
Theme songs, vocal spots, and lyric-locked beds. If you arrived with the words already written and you need the model to sing them, that is this model. An instrumental version of the same track is available when it has to sit under narration.