Skill detail

minimax-music

Produces music with MiniMax Music 2.6 and cover/lyrics APIs for songs, instrumentals, and covers with rights checks and production QA.

MatchDirectReviewed for Music Generation
Sourcecalesthio/​generative-media-skillsExternal source
Reported installs66Popularity signal only

Inspect before use

Automated review checks relevance, not safety or endorsement. Read the source instructions before using this skill.

Saved source preview

SKILL.md

The saved excerpt is a snapshot from review. The external source remains the complete and most current version.

---
name: minimax-music
description: Produce music with MiniMax Music 2.6 and MiniMax cover/lyrics APIs for songs, instrumentals, AI-generated lyrics, reference-audio covers, video/social/ad soundtracks, artifact custody, rights checks, and production QA.
---

# MiniMax Music production

Use MiniMax Music when the job needs an original song, instrumental bed, theme, jingle, or cover-style rendition from a style prompt, lyrics, or authorized reference audio. Treat it as a music-production provider, not a generic sound-effects tool.

The current public API surface verified on 2026-07-10 is:

- `POST https://api.minimax.io/v1/music_generation` for text-to-music, instrumental music, and cover generation.
- `POST https://api.minimax.io/v1/lyrics_generation` for complete lyrics or lyrics editing/continuation.
- `POST https://api.minimax.io/v1/music_cover_preprocess` for extracting a reference track's feature ID, structured lyrics, and rough structure before an editable cover workflow.
- Global docs list `https://api.minimax.io`; some ecosystem tooling distinguishes a China endpoint such as `https://api.minimaxi.com`. If authentication fails with a valid key, verify the user's account region and configured base URL rather than repeatedly retrying.

Sources verified 2026-07-10: MiniMax music guide, API reference, lyrics API reference, cover preprocess reference, rate-limit guide, pay-as-you-go pricing guide, unified terms, Audio Music Creation Terms, and privacy overview:

- https://platform.minimax.io/docs/guides/music-generation
- https://platform.minimax.io/docs/api-reference/music-generation
- https://platform.minimax.io/docs/api-reference/lyrics-generation
- https://platform.minimax.io/docs/api-reference/music-cover-preprocess
- https://platform.minimax.io/docs/guides/rate-limits
- https://platform.minimax.io/docs/guides/pricing-paygo
- https://www.minimax.io/terms-of-service-v2.html
- https://www.minimax.io/audio/doc/terms-of-service-music.html
- https://www.minimax.io/privacy-policy-v2.html

## Route the job

Choose one of these routes before generating:

1. Original song with user-supplied lyrics: call `music_generation` with `model: "music-2.6"` or `music-2.6-free`, a production-style `prompt`, and the supplied `lyrics`.
2. Original song without lyrics: use `lyrics_generation` first, or set `lyrics_optimizer: true` with empty lyrics when using `music-2.6`/`music-2.6-free`. Prefer a separate lyrics pass when the words matter, because you can review structure, brand safety, and rhyme before paying for audio.
3. Instrumental: call `music_generation` with `is_instrumental: true`; omit `lyrics`. The prompt becomes mandatory and should specify genre, mood, instrumentation, energy arc, use case, and edit constraints.
4. Quick cover from authorized reference audio: call `music_generation` with `model: "music-cover"` or `music-cover-free`, `audio_url` or `audio_base64`, and a target style prompt. This extracts lyrics automatically if `lyrics` is omitted.
5. Editable cover from authorized reference audio: call `music_cover_preprocess` first, review/modify `formatted_lyrics`, then call `music_generation` with `cover_feature_id` and the edited lyrics.

Do not use cover mode unless the user owns or has licensed the reference audio, performance, voice, and lyrics rights needed for the intended use. MiniMax's Audio Music Creation terms require rights or authorization for input content, including audio, lyrics, music, voices, and works; if an input includes a person's voice, authorization is required.

## Current API facts to preserve

Facts below are documented by MiniMax and were verified on 2026-07-10.

Model choices:

- `music-2.6`: recommended text-to-music model; available to Token Plan and paid users, with higher RPM.
- `music-2.6-free`: free-tier text-to-music model; available through API key, with lower RPM.
- `music-cover`: reference-audio cover model; paid/Token Plan tier.
- `music-cover-free`: free-tier reference-audio cover mode
Read the full source on GitHub (opens external page)
Context

Related work