# AI music: the complete guide

> Updated: 2026-10-30 · Applies to KiiKii
> HTML version: https://kiikii.cc/en/doc/music

## Quick answer

- Two paths: Inspire Mode writes a song through conversation; Advanced Mode takes a title, style, lyrics, and ABC notation directly.
- Four post-production tools: Lyric Cover, Voice Cover, Stem Separation, and MIDI Conversion.
- ABC notation is a plain-text melody notation; you can skip it entirely if you do not read music.
- A finished track can be sent to the digital human Music MV mode in one click, with duration following the song.
- Run one 1–2 minute song through Inspire Mode first, then try Advanced Mode and the post-production tools.

## 1. What music generation can do
AI music puts lyric writing, style definition, vocal generation, post-production tools, and MV creation into one pipeline: generate a song, then separate stems, convert to MIDI, re-sing it with new lyrics, and bring it into a digital human to produce an MV. Whether you get a full song or an instrumental depends on the creation type—Instrumental BGM contains no vocals or lyrics and suits voice-over, retail, and video backgrounds, while only the song type produces sung vocals.

## 2. Inspire Mode
Best when you have only a vague idea: describe the scenario, mood, and use case, and the AI asks for key details before returning an editable creation card. You can set genre, language, vocal, mood, and duration under Composition Preferences (up to three genres); the card's title, style, and lyrics are editable, and after Generate Now the track goes to your library for preview, version switching, or post-production.

## 3. Advanced Mode
When you know what you want, fill in creation type, title, music style, lyrics, optional ABC notation, and duration in one form. Style accepts a Chinese description that is translated before generation, so state genre, instruments, tempo, mood, and vocal type rather than only "nice" or "sad"; mark lyrics with [Intro] [Verse] [Chorus] [Bridge] [Outro]. Songs are estimated from lyric length up to about 5 minutes, while BGM lets you pick seconds directly.

## 4. ABC notation basics
ABC notation is a plain-text format that records melody with letters and symbols, and it can be copied, pasted, and read by AI as a melodic skeleton. The header has X (sequence number), T (title), M (time signature), L (default note value), Q (tempo), and K (key); in the body A–G are pitches, a comma marks the lower octave and an apostrophe the higher one, numbers set note length (A2 is twice, A/2 is half), z is a rest, | is a bar line, and [CEG] is a chord. Lyrics can go on w: lines aligned to the note order.

## 5. Lyric Cover
Upload a reference track and the AI extracts its melodic structure, then re-sings it with your new lyrics and style—useful for localizing a brand theme song, adapting a track for an event, or making multilingual versions of the same melody. The reference accepts mp3 / wav / flac / m4a up to 20 MB, and you enter new lyrics plus an English style description of at least 10 characters; the new version sits alongside the old one so you can switch and compare.

## 6. Voice Cover
One step beyond lyric cover: the reference track supplies the melody, a dry vocal reference decides the timbre, and the song is re-sung with your new lyrics. Timbre strength controls how closely the result follows the reference (default 0.8; too high can cost naturalness). Use it to sing a melody in your own cloned timbre or build a brand-exclusive vocal version; to keep the original singer's timbre, use Lyric Cover instead.

## 7. Stem separation
Stem separation splits finished audio into four independent tracks: vocals (dry a cappella, for timbre reference or re-editing), instrumental (backing with vocals removed, for karaoke or voice-over), drums (percussion rhythm, for beat sync and re-arranging), and bass (low-frequency track, for mixing and low-end design). Quality depends on the source mix; vocals and instrumental can never be split with zero residue, and dialogue or heavily reverberant material separates less cleanly.

## 8. MIDI conversion
MIDI conversion detects the vocal melody and produces a .mid file you can open in arranging software, and choosing Chinese or English vocals affects lyric recognition and melody extraction accuracy. Use it to edit the melody, change timbres, make an instrumental or orchestral version, export a score, or move the melody onto another backing track; it extracts the main melody, not full multi-track stems, so run Stem Separation for that.

## 9. Generate an MV with a digital human
On the song detail page, click Generate MV Video and the system carries the song URL and title into the digital human Music MV mode with the song already filled in. Choose the avatar, an optional second avatar, and MV direction (for example a rainy street at night with warm and cool light and a push-in on the chorus), then pick aspect ratio and resolution; MV duration follows the song, so no target length is needed.

## 10. Showcase
Four finished tracks show the range: "Breaking the Cage" (high-energy rock), "Empty Cup" (Guofeng narrative), "Snowfall Says I Love You" (lyrical pop), and "Hangzhou Girl" (urban folk). Listen for vocal clarity and diction, a memorable chorus, attention in the first 15 seconds, and layered arrangement; the examples demonstrate timbre and arrangement only, so confirm licensing before commercial release.

## FAQ

### How do I choose between Inspire Mode and Advanced Mode?
Use Inspire Mode for a vague first idea and talk through theme, genre, language, vocal, and mood. Use Advanced Mode when you know the title, style, and lyrics, or need ABC notation and an exact duration. Tracks from both modes go to your library.
### Do I need to learn ABC notation if I don't read music?
No. Without ABC notation, write lyrics and style in Inspire Mode or Advanced Mode. ABC notation is for people who already have a definite melody to fix in place, or who get ABC text from an external tool.
### What is ABC notation?
ABC notation records melody as plain text: X is the sequence number, T the title, M the time signature, L the default note value, Q the tempo, and K the key; A–G are pitches, z is a rest, and | is a bar line. It is easier than staff notation to copy, paste, and have an AI read.
### What is the difference between Lyric Cover and Voice Cover?
Lyric Cover keeps the melodic structure and re-sings it with new lyrics and style. Voice Cover also needs a dry vocal reference so the performance moves closer to the specified timbre. The first changes the words; the second changes the words and the voice.
### What is stem separation actually used for?
It splits a finished track into vocals, instrumental, drums, and bass. The vocal stem can serve as a timbre reference, the instrumental works as karaoke or cover backing, and drums and bass serve re-arranging, mixing, or beat-synced short videos.
### What can MIDI conversion do?
It extracts the main melody from the vocals into a .mid file for arranging software, suitable for changing the melody, swapping timbres, making an instrumental version, or re-arranging in a DAW. It is not a full multi-track split.
### How do I turn a generated song into an MV?
On the song detail page, click Generate MV Video. The song URL and title carry into the digital human Music MV mode; choose the avatar, second avatar, and visual style, then generate. MV duration follows the song.
### Can generated music be used commercially?
Make sure you hold the necessary rights to lyrics, melody, reference audio, voice samples, and avatar assets, and comply with platform rules and local law. Do not cover others' works, clone others' voices, or use copyrighted reference tracks without authorization.