Music and Voices

Status: Approved initial tool direction; prompt format remains Candidate

Suno is always the first media-generation stage. After the episode concept, learning goal, and story/song brief are approved, Suno generates both music and narration. No Anima storyboard or Wan shot production begins until a specific Suno version is selected, imported into Palmier, transcribed with Whisper, and converted into a reviewed timing map.

The working pipeline is strongest when a piece is designed for two distinct voices, uses explicit spoken-word tags, and describes the emotional movement of each section.

The selected Suno audio on the Palmier timeline is the episode’s timing and emotional spine. Whisper provides the timecoded transcript used to place shot boundaries. The storyboard interprets that audio; the audio is not reshaped to justify an already-generated storyboard.

Voice functions

Voice	Dramatic job
Lumi	Ground the idea, model listening, carry reassurance and wonder
Pip	Create momentum, ask the active question, embody surprise and play
Together	Deliver the hook and the shared discovery

The functions can swap for story reasons, but the voices should never feel interchangeable.

Song brief structure

song:
  episode: S01E__
  letter: ""
  duration_target: ""
  emotional_arc: curious -> uncertain -> delighted -> warm
  spoken_word:
    opening: "[Lumi, softly spoken]"
    pivot: "[Pip, excited spoken interjection]"
  sections:
    - intro
    - call_and_response_verse
    - chorus
    - discovery_bridge
    - final_chorus
    - gentle_button
  hook: ""
  anchor_words: []
  generation_record:
    tool: Suno
    output_mode: integrated_music_and_narration
    prompt_version: ""
    output_link: ""
    status: Draft
  audio_lock:
    selected_version: ""
    duration: ""
    palmier_project: ""
    palmier_audio_track: ""
    whisper_transcript: ""
    whisper_timing_map: ""
    locked_on: YYYY-MM-DD

For episodes where control is stronger with separate generations, preserve distinct music_output and narration_output records and document how they are combined in Palmier.

Rules

• Give each voice an intention and feeling, not just a name.
• Use spoken tags where story clarity matters.
• Let the chorus express the discovery, not merely repeat the letter.
• Write visual beats and song structure together.
• Preserve generation prompts and selected output links.
• Import the chosen Suno version into Palmier before Anima storyboarding.
• Run Whisper on the exact imported song and preserve the timecoded transcript.
• Review Whisper’s words against the approved lyrics while retaining verified timing; sung words can require text correction.
• Lock the reviewed transcript and shot timing map before Anima storyboarding.
• Treat any later audio change as a dependency change that may invalidate the storyboard, Wan shots, and Palmier timeline.