leemysw/yovoice/yovoice-music

YuE2 music (YuE2 音乐)

YuE2 renders a song from a style prompt, lyrics and, optionally, a two-voice melody score (abc field: Vocal with chords, Ins instrumental melody). Call get_work first: text is the style, settings.lyrics the lyrics, settings.abc the score, settings.instrumental the instrumental switch, settings.modelOptions.yue2 the generation settings.

Style and lyrics

• Style in English tags, in this order: sung language, genre, instruments, vocal character, mood, tempo — e.g. English, warm piano pop, expressive female voice, acoustic piano, light drums, unhurried phrasing, 88 BPM. Put tempo and meter in the score too and keep them consistent.
• Lyrics: section tags on their own lines ([Verse], [Chorus], [Bridge], [Outro]) followed by the sung words. Only words to be sung; no notes or instructions. Song length follows the lyrics.

Pick the workflow

Reference files are in this skill's folder (from the workspace: .agents/skills/yovoice-music/references/); read only the one the task needs.

Settings

modelOptions.yue2: cot (auto | full | melody | off; auto picks full with chords, melody without), num_inference_steps 1-64 (8; more steps can sound cleaner but take longer), abc_temperature 0.05-2 (0.7, score writing), semantic_temperature 0.05-2 (1.0), semantic_top_p 0.01-1 (0.95), semantic_top_k 1-500 (100), semantic_repetition_penalty 0.5-3 (1.2). Change them only when asked; the defaults are the tuned route.

Be honest about results

YuE2 follows a score loosely: it does not guarantee every note, exact timing, or that an instrument named in the style is absent. A valid score or a finished take is not proof it sounds right; say what you changed and invite the user to listen. Every edit becomes a new take; earlier takes stay in the history for comparison.