# Fish Video Skill defaults. A project's brief.yaml overrides any of these
# keys (deep merge). Numbers here are the tested defaults, not suggestions.

tempo:
  bpm: 120            # one bar = 2.0 s; every cut lands on a bar line
  beats_per_bar: 4

pacing:
  lead_in: 0.35       # s from scene start to the first spoken word
  line_gap: 0.30      # s breath between narration lines inside a scene
  tail: 0.55          # s after the last word before the cut
  wpm:                # speaking rate used to estimate before TTS exists
    default: 150
    en-IN: 145
    en-US: 155
    en-GB: 150
    hi-IN: 130
    es: 160
    fr: 150
    de: 140
  min_scene:          # s a scene needs on screen even without narration
    title: 4.0
    kinetic: 3.0
    bullets: 4.0
    stat: 4.0
    chart: 5.0
    diagram: 5.0
    whiteboard: 6.0
    steps: 5.0
    quote: 4.0
    compare: 5.0
    terminal: 5.0
    tour: 4.0
    image: 4.0
    end: 4.0
    thumbnail: 1.0

# Voice. Default: the ElevenLabs voice chosen for ImuTechz (English, India).
# Without ELEVENLABS_API_KEY (environment or the project/skill .env) the
# free edge-tts fallback is used and the build says so.
voice:
  provider: elevenlabs
  language: en-IN
  elevenlabs:
    voice_id: fydPJq00SigRIaPxWgiS
    voice_url: https://elevenlabs.io/voices/fydPJq00SigRIaPxWgiS
    model_id: eleven_multilingual_v2
    language_code: null
    output_format: mp3_44100_128
    voice_settings:
      stability: 0.42
      similarity_boost: 0.8
      style: 0.18
      use_speaker_boost: true
      speed: 0.96
    use_context: true
    max_speed: 1.12
  fallback:
    provider: edge-tts
    voice: en-IN-NeerjaNeural
    rate: "-6%"
    pitch: "+0Hz"
    volume: "+0%"
    max_rate: "+8%"
  # applied to the voice track: rumble cut, low-mid cleanup, presence + air, gentle compression, a short soft room
  post: "highpass=f=85,equalizer=f=280:t=q:w=1.2:g=-2,equalizer=f=4800:t=q:w=1.4:g=1.5,highshelf=f=9000:g=3,acompressor=threshold=-20dB:ratio=2.5:attack=8:release=120:makeup=2,aecho=0.9:0.9:23|41:0.07|0.04"

# Three stems (references/sound-design.md). Numbers come from measuring the reference Shorts.
mix:
  voice_lufs: -16            # voice stem level before summing
  music_under_voice_db: -10  # music under the voice, measured ON A SIMULATED PHONE SPEAKER, so it stays audible everywhere
  music_max_fullband_db: -8  # ...but never louder than this under the voice full-range (headphones stay balanced)
  music_carve_db: -1.5       # gentle static mid dip; the duck makes room for words. A deep dip kills music on phones
  translate:                 # small-speaker translation: bass harmonics the ear hears as bass (references/sound-design.md)
    music_drive_db: 14
    music_harmonics_db: -4
    music_width: 0.85        # slightly narrower stereo, so a mono phone speaker does not cancel it
    sfx_drive_db: 16
    sfx_harmonics_db: -6
  sfx_gain_db: 0             # manual trim on the SFX stems (never ducked)
  sfx_under_voice_db: -7     # on a phone, a typical SFX event peaks this far under typical speech (auto-calibrated)
  sfx_max_boost_db: 12
  duck:                      # sidechain: the voice ducks the music ~6 dB while speaking
    threshold: 0.05
    ratio: 3
    attack: 10
    release: 250
    makeup: 1
  loudness: -14            # LUFS integrated (overridden per platform)
  true_peak: -1.5          # dBTP
  lra: 11

score:
  key: D
  mode: minor
  progression: i-VI-III-VII
  seed: 12345
  drums: true
  sfx: true

captions:
  max_chars: 42
  max_lines: 2
  min_cue: 0.9            # s
  max_cps: 20             # characters per second (reading speed)

# Platform profiles. safe = margins (px) kept clear of UI overlays; scenes
# lay out inside them, burned-in captions sit just above the bottom one.
platforms:
  youtube:
    label: YouTube
    W: 1920
    H: 1080
    fps: 30
    safe: {top: 70, right: 110, bottom: 80, left: 110}
    burn_captions: false
    crf: 18
    maxrate: 16M
    bufsize: 32M
    audio_bitrate: 192k
    loudness: -14
    true_peak: -1.5
    max_seconds: null
    captions: {max_chars: 42, max_lines: 2}
    min_text_px: 22
  linkedin:
    label: LinkedIn (4:5)
    W: 1080
    H: 1350
    fps: 30
    safe: {top: 70, right: 64, bottom: 80, left: 64}
    burn_captions: true
    crf: 19
    maxrate: 10M
    bufsize: 20M
    audio_bitrate: 192k
    loudness: -14
    true_peak: -1.5
    max_seconds: 600
    captions: {max_chars: 32, max_lines: 2}
    min_text_px: 24
  linkedin-square:
    label: LinkedIn (1:1)
    W: 1080
    H: 1080
    fps: 30
    safe: {top: 60, right: 64, bottom: 64, left: 64}
    burn_captions: true
    crf: 19
    maxrate: 10M
    bufsize: 20M
    audio_bitrate: 192k
    loudness: -14
    true_peak: -1.5
    max_seconds: 600
    captions: {max_chars: 32, max_lines: 2}
    min_text_px: 24
  shorts:
    label: YouTube Shorts (9:16)
    W: 1080
    H: 1920
    fps: 30
    safe: {top: 240, right: 140, bottom: 420, left: 64}
    burn_captions: true
    crf: 19
    maxrate: 12M
    bufsize: 24M
    audio_bitrate: 192k
    loudness: -12
    true_peak: -1.0
    max_seconds: 180
    captions: {max_chars: 26, max_lines: 2}
    min_text_px: 28
  reels:
    label: Instagram Reels (9:16)
    W: 1080
    H: 1920
    fps: 30
    safe: {top: 250, right: 140, bottom: 480, left: 64}
    burn_captions: true
    crf: 19
    maxrate: 10M
    bufsize: 20M
    audio_bitrate: 192k
    loudness: -12
    true_peak: -1.0
    max_seconds: 90
    captions: {max_chars: 26, max_lines: 2}
    min_text_px: 28
  tiktok:
    label: TikTok (9:16)
    W: 1080
    H: 1920
    fps: 30
    safe: {top: 220, right: 160, bottom: 460, left: 64}
    burn_captions: true
    crf: 19
    maxrate: 10M
    bufsize: 20M
    audio_bitrate: 192k
    loudness: -12
    true_peak: -1.0
    max_seconds: 600
    captions: {max_chars: 26, max_lines: 2}
    min_text_px: 28
  x:
    label: X (16:9)
    W: 1920
    H: 1080
    fps: 30
    safe: {top: 70, right: 110, bottom: 90, left: 110}
    burn_captions: true
    crf: 20
    maxrate: 12M
    bufsize: 24M
    audio_bitrate: 128k
    loudness: -14
    true_peak: -1.5
    max_seconds: 140
    captions: {max_chars: 42, max_lines: 2}
    min_text_px: 22
  thumbnail:
    label: Thumbnail
    W: 1280
    H: 720
    fps: 30
    safe: {top: 40, right: 56, bottom: 40, left: 56}
    burn_captions: false