MiniMax Music
Prompt-driven music generation with vocals — full songs from text descriptions and lyrics.
About
MiniMax Music (now at version 2.5) generates complete songs with both singing voices and instrumental arrangements from natural-language prompts plus lyrics. Describe a genre blend, mood, tempo, and vocal style — e.g. synthwave mixed with traditional Chinese instruments — and get a finished track in seconds. It also handles stems, variations, background music, and audio logos, exposed through MiniMax's developer API alongside their Hailuo video and speech models.
MiniMax iterates fast: Music 1.5 added 4-minute songs, 2.0 deepened emotional expression, and 2.5 promises finer control. As with all AI music tools, check the commercial-use terms on your plan before using outputs in client work, and expect the usual AI-music caveats around originality and repetitive structure on longer generations.
What it can do
- Full songs with AI vocals from text prompts
- Genre/mood/tempo/vocal-style control
- Up to 4-minute generations
- Stem separation and variations
- Background music and audio logos
- REST API alongside Hailuo video models
Setup
Use via the MiniMax platform API (platform.minimax.io) or third-party API aggregators. Provide a style prompt plus lyrics to generate a vocal song.
Prerequisites
A MiniMax API key; lyrics if you want vocal tracks.
Use cases
Works with
Trust score — 7/10
Scored 7/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 49; Trending score 68/100 from researcher assessment.
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.