Why lyrics vanish when AI writes your music prompt

What makes this hard

Music tools usually take two fields — style, which sets the sound, and lyrics. Ask AI for the prompt and one side often comes back empty: [Verse 1] [Chorus] part labels with descriptions like 'this part follows the commute-home gaze' — and nothing to actually sing. Paste that in and the engine invents its own words, different on every run.

The other trap is values left blank. Leave tempo and key 'to taste' and the decision passes to the engine — a different song every time. An empty field isn't humility; it's a randomizer button.

What to add to the request

1. Demand both blocks: style and lyrics

2. Unknown values come back as recommendations

Genre implies a usual range for tempo and key. Ask it to propose value plus basis — '92 BPM, the usual range for mellow city pop; say the word to go faster' — and you get a decided prompt without knowing the values yourself. Same for instrumentation and dynamics: not 'stronger in the chorus' but which parts enter and which drop, as values.

3. Separate keep from avoid

• Lyric lines you provided stay verbatim — it builds around them
• No reproducing existing melodies or lyrics; no naming a specific artist as the vocal target
• Lyrics must fit the melody in syllable count and breath, not just meaning — require even line lengths

Checklist for writing it yourself

1. 1Did you require both the style block and the lyrics block
2. 2Do the lyrics contain actual words to sing, not only part tags
3. 3Did tempo, key, and instrumentation come as values or recommendations
4. 4Did you specify vocal timbre, gender, delivery — and for an album, the track-to-track consistency step
5. 5For an instrumental, did you forbid the lyrics field