Songwriting And AI Music

Operational Steps

1. 确认输入参数完整
2. 执行核心操作（参考本目录下的 scripts/ 或 references/）
3. 验证输出符合契约
4. 保存结果并报告

Pitfalls

-

-

Verification

-

-

-

-

1. 2. 3.

IO_CONTRACT

• input: request: str, context: dict — 用户请求描述、上下文信息
• output: result: dict — 技能执行结果（结构因技能而异）

对应原则：P2（机械原子暴露输入输出规范）

Songwriting & AI Music Generation

Everything here is a GUIDELINE, not a rule. Art breaks rules on purpose. Use what serves the song. Ignore what doesn't.

1. Song Structure (Pick One or Invent Your Own)

Common skeletons — mix, modify, or throw out as needed:

ABABCB  Verse/Chorus/Verse/Chorus/Bridge/Chorus    (most pop/rock)
AABA    Verse/Verse/Bridge/Verse (refrain-based)    (jazz standards, ballads)
ABAB    Verse/Chorus alternating                    (simple, direct)
AAA     Verse/Verse/Verse (strophic, no chorus)     (folk, storytelling)

The six building blocks:

• Intro — set the mood, pull the listener in
• Verse — the story, the details, the world-building
• Pre-Chorus — optional tension ramp before the payoff
• Chorus — the emotional core, the part people remember
• Bridge — a detour, a shift in perspective or key
• Outro — the farewell, can echo or subvert the rest

You don't need all of these. Some great songs are just one section that evolves. Structure serves the emotion, not the other way around.

2. Rhyme, Meter, and Sound

RHYME TYPES (from tight to loose):

• Perfect: lean/mean
• Family: crate/braid
• Assonance: had/glass (same vowels, different endings)
• Consonance: scene/when (different vowels, similar endings)
• Near/slant: enough to suggest connection without locking it down

Mix them. All perfect rhymes can sound like a nursery rhyme. All slant rhymes can sound lazy. The blend is where it lives.

INTERNAL RHYME: Rhyming within a line, not just at the ends. "We pruned the lies from bleeding trees / Distilled the storm from entropy" — "lies/flies," "trees/entropy" create internal echoes.

METER: The rhythm of stressed vs unstressed syllables.

• Matching syllable counts between parallel lines helps singability
• The STRESSED syllables matter more than total count
• Say it out loud. If you stumble, the meter needs work.
• Intentionally breaking meter can create emphasis or surprise

3. Emotional Arc and Dynamics

Think of a song as a journey, not a flat road.

ENERGY MAPPING (rough idea, not prescription): Intro: 2-3 | Verse: 5-6 | Pre-Chorus: 7 Chorus: 8-9 | Bridge: varies | Final Chorus: 9-10

The most powerful dynamic trick: CONTRAST.

• Whisper before a scream hits harder than just screaming
• Sparse before dense. Slow before fast. Low before high.
• The drop only works because of the buildup
• Silence is an instrument

"Whisper to roar to whisper" — start intimate, build to full power, strip back to vulnerability. Works for ballads, epics, anthems.

4. Writing Lyrics That Work

SHOW, DON'T TELL (usually):

• "I was sad" = flat
• "Your hoodie's still on the hook by the door" = alive
• But sometimes "I give my life" said plainly IS the power

THE HOOK:

• The line people remember, hum, repeat
• Usually the title or core phrase
• Works best when melody + lyric + emotion all align
• Place it where it lands hardest (often first/last line of chorus)

PROSODY — lyrics and music supporting each other:

• Stable feelings (resolution, peace) pair with settled melodies, perfect rhymes, resolved chords
• Unstable feelings (longing, doubt) pair with wandering melodies, near-rhymes, unresolved chords
• Verse melody typically sits lower, chorus goes higher
• But flip this if it serves the song

AVOID (unless you're doing it on purpose):

• Cliches on autopilot ("heart of gold" without earning it)
• Forcing word order to hit a rhyme ("Yoda-speak")
• Same energy in every section (flat dynamics)
• Treating your first draft as sacred — revision is creation

5. Parody and Adaptation

When rewriting an existing song with new lyrics:

THE SKELETON: Map the original's structure first.

• Count syllables per line
• Mark the rhyme scheme (ABAB, AABB, etc.)
• Identify which syllables are STRESSED
• Note where held/sustained notes fall

FITTING NEW WORDS:

• Match stressed syllables to the same beats as the original
• Total syllable count can flex by 1-2 unstressed syllables
• On long held notes, try to match the VOWEL SOUND of the original (if original holds "LOOOVE" with an "oo" vowel, "FOOOD" fits better than "LIFE")
• Monosyllabic swaps in key spots keep rhythm intact (Crime -> Code, Snake -> Noose)
• Sing your new words over the original — if you stumble, revise

CONCEPT:

• Pick a concept strong enough to sustain the whole song
• Start from the title/hook and build outward
• Generate lots of raw material (puns, phrases, images) FIRST, then fit the best ones into the structure
• If you need a specific line somewhere, reverse-engineer the rhyme scheme backward to set it up

KEEP SOME ORIGINALS: Leaving a few original lines or structures intact adds recognizability and lets the audience feel the connection.

6. Suno AI Prompt Engineering

Style/Genre Description Field

FORMULA (adapt as needed): Genre + Mood + Era + Instruments + Vocal Style + Production + Dynamics

BAD:  "sad rock song"
GOOD: "Cinematic orchestral spy thriller, 1960s Cold War era, smoky
       sultry female vocalist, big band jazz, brass section with
       trumpets and french horns, sweeping strings, minor key,
       vintage analog warmth"

DESCRIBE THE JOURNEY, not just the genre:

"Begins as a haunting whisper over sparse piano. Gradually layers
 in muted brass. Builds through the chorus with full orchestra.
 Second verse erupts with raw belting intensity. Outro strips back
 to a lone piano and a fragile whisper fading to silence."

TIPS:

• V4.5+ supports up to 1,000 chars in Style field — use them
• NO artist names or trademarks. Describe the sound instead. "1960s Cold War spy thriller brass" not "James Bond style" "90s grunge" not "Nirvana-style"
• Specify BPM and key when you have a preference
• Use Exclude Styles field for what you DON'T want
• Unexpected genre combos can be gold: "bossa nova trap", "Appalachian gothic", "chiptune jazz"
• Build a vocal PERSONA, not just a gender: "A weathered torch singer with a smoky alto, slight rasp, who starts vulnerable and builds to devastating power"

Metatags (place in [brackets] inside lyrics field)

STRUCTURE: [Intro] [Verse] [Verse 1] [Pre-Chorus] [Chorus] [Post-Chorus] [Hook] [Bridge] [Interlude] [Instrumental] [Instrumental Break] [Guitar Solo] [Breakdown] [Build-up] [Outro] [Silence] [End]

VOCAL PERFORMANCE: [Whispered] [Spoken Word] [Belted] [Falsetto] [Powerful] [Soulful] [Raspy] [Breathy] [Smooth] [Gritty] [Staccato] [Legato] [Vibrato] [Melismatic] [Harmonies] [Choir] [Harmonized Chorus]

DYNAMICS: [High Energy] [Low Energy] [Building Energy] [Explosive] [Emotional Climax] [Gradual swell] [Orchestral swell] [Quiet arrangement] [Falling tension] [Slow Down]

GENDER: [Female Vocals] [Male Vocals]

ATMOSPHERE: [Melancholic] [Euphoric] [Nostalgic] [Aggressive] [Dreamy] [Intimate] [Dark Atmosphere]

SFX: [Vinyl Crackle] [Rain] [Applause] [Static] [Thunder]

Put tags in BOTH style field AND lyrics for reinforcement. Keep to 5-8 tags per section max — too many confuses the AI. Don't contradict yourself ([Calm] + [Aggressive] in same section).

Custom Mode

• Always use Custom Mode for serious work (separate Style + Lyrics)
• Lyrics field limit: 3,000 chars (40-60 lines)
• Always add structural tags — without them Suno defaults to flat verse/chorus/verse with no emotional arc

7. Phonetic Tricks for AI Singers

AI vocalists don't read — they pronounce. Help them:

PHONETIC RESPELLING:

• Spell words as they SOUND: "through" -> "thru"
• Proper nouns are highest failure rate — test early
• "Nous" -> "Noose" (forces correct pronunciation)
• Hyphenate to guide syllables: "Re-search", "bio-engineering"

DELIVERY CONTROL:

• ALL CAPS = louder, more intense
• Vowel extension: "lo-o-o-ove" = sustained/melisma
• Ellipses: "I... need... you" = dramatic pauses
• Hyphenated stretch: "ne-e-ed" = emotional stretch

ALWAYS:

• Spell out numbers: "24/7" -> "twenty four seven"
• Space acronyms: "AI" -> "A I" or "A-I"
• Test proper nouns/unusual words in a short 30-second clip first
• Once generated, pronunciation is baked in — fix in lyrics BEFORE

8. Workflow

1. Write the concept/hook first — what's the emotional core?
2. If adapting, map the original structure (syllables, rhyme, stress)
3. Generate raw material — brainstorm freely before structuring
4. Draft lyrics into the structure
5. Read/sing aloud — catch stumbles, fix meter
6. Build the Suno style description — paint the dynamic journey
7. Add metatags to lyrics for performance direction
8. Generate 3-5 variations minimum — treat them like recording takes
9. Pick the best, use Extend/Continue to build on promising sections
10. If something great happens by accident, keep it

EXPECT: ~3-5 generations per 1 good result. Revision is normal. Style can drift in extensions — restate genre/mood when extending.

9. Lessons Learned

• Describing the dynamic ARC in the style field matters way more than just listing genres. "Whisper to roar to whisper" gives Suno a performance map.
• Keeping some original lines intact in a parody adds recognizability and emotional weight — the audience feels the ghost of the original.
• The bridge slot in a song is where you can transform imagery. Swap the original's specific references for your theme's metaphors while keeping the emotional function (reflection, shift, revelation).
• Monosyllabic word swaps in hooks/tags are the cleanest way to maintain rhythm while changing meaning.
• A strong vocal persona description in the style field makes a bigger difference than any single metatag.
• Don't be precious about rules. If a line breaks meter but hits harder, keep it. The feeling is what matters. Craft serves art, not the other way around.

验证清单 · VERIFICATION

• Suno Style 字段遵循"流派+情绪+时代+乐器+人声+制作"公式，且描述的是动态旅程（如 whisper→roar）而非仅罗列流派；无艺术家名或商标
• 歌词元标签每节 5-8 个且互相不矛盾（同一节内无 [Calm]+[Aggressive] 并存），关键标签在 Style 与 Lyrics 两处均出现
• 专有名词、数字、缩写已做音韵处理（数字拼写、缩写加空格、非常见词先用 30 秒片段试发音）
• 使用 Custom Mode 且歌词含结构标签 [Verse]/[Chorus]/[Bridge] 等，避免 Suno 默认平直 verse/chorus 无情感弧线
• 已生成 ≥3 个变体再择优；Extend/Continue 时重申 genre/mood 以防风格漂移
• 歌词朗读/跟唱无顿挫（重音音节与节拍对齐），押韵混合了完美韵与近韵而非单一类型

约束规则 · RULES

1. 输入约束: 参数类型、范围、格式必须校验
2. 输出约束: 返回值结构、编码、命名必须一致
3. 异常约束: 错误信息必须包含上下文和恢复建议
4. 安全约束: 不执行未验证的任意代码，不暴露内部状态

Golden 集合 · GOLDEN SET

• Golden Input: 标准输入样本（覆盖正常路径）
• Golden Output: 预期输出（精确匹配或格式校验）
• Golden Error: 预期错误信息（覆盖失败路径）

Golden 集合是测试的单一真理来源。所有改进必须通过 golden 测试。

违反规则的操作视为不安全，必须拒绝或隔离。

每项验证必须可执行、可记录、可复现。验证失败时记录原因和修复。

Songwriting And Ai Music

Genes (策略基因)

紧凑策略表示。条件→策略。需要深度时参考完整文档。

• [SONG-008] 当需要构建歌曲结构时 → 根据情感需求选择骨架（如 ABABCB），让结构服务于情绪而非反之
• [SONG-009] 当处理韵律与节奏时 → 混合使用完美押韵与近韵，并优先确保重音音节匹配以保障可唱性
• [SONG-010] 当设计动态变化时 → 利用对比原则（如先低后高、先静后动）来增强情感冲击力，将沉默视为乐器
• [SONG-011] 当撰写歌词意象时 → 遵循“展示而非告知”原则，用具体细节代替抽象情感，除非平实陈述本身具有力量
• [SONG-012] 当进行改编或戏仿时 → 先映射原曲的音节数、重音及韵脚骨架，再填入新词并保留部分原句以维持辨识度
• [SONG-013] 当编写 AI 音乐风格提示词时 → 使用“流派+情绪+时代+乐器+人声+制作”公式，描述声音旅程而非仅指定流派
• [SONG-007] 当使用元标签控制生成时 → 在歌词中嵌入 5-8 个不冲突的结构/动态/氛围标签，并在风格字段中同步强化

示例 · EXAMPLES

1. 写一首"低语到嘶吼"的 cinematic ballad（Suno Custom Mode）

   • 输入: 情感核 = 失去后的释然，结构选 ABABCB。
   • 操作: 按 流派+情绪+时代+乐器+人声+制作 公式写 Style（如 "sparse piano ballad, minor key, weathered alto, builds from whisper to full orchestra"）；歌词嵌入 [Verse]/[Chorus]/[Bridge] 结构标签，每节 5-8 个不冲突标签，Style 与 Lyrics 双处强化。
   • 验证: 朗读歌词无顿挫；生成 ≥3 个变体择优；Extend 时重申 genre/mood 防漂移。

2. 戏仿改编已有歌曲

   • 输入: 原曲歌词 + 新主题概念。
   • 操作: 逐行统计音节数、标注韵式与重音；新词重音对齐原节拍，长延音处匹配原元音，单音节词做干净替换（Crime→Code），保留数句原词增加辨识度。
   • 验证: 新词跟唱原曲不磕绊；保留原句存在且新主题贯穿全曲。

3. AI 歌手发音纠错

   • 输入: 含专有名词 "Nous" 与数字 "24/7" 的歌词行。
   • 操作: 音韵改拼 "Nous"→"Noose"，数字拼出 "twenty four seven"；先跑 30 秒短片段试发音。
   • 验证: 短片段中发音正确后再全曲生成；发音一旦烘焙进音频只能在歌词层面重改。