VOICE REQUEST
    |
    |-- Have reference audio of target voice?
    |   |-- Yes (5+ seconds) → Chatterbox (MIT, paralinguistic tags)
    |   |-- Yes (10-15 seconds) → F5-TTS (fastest zero-shot)
    |   |-- Yes (10+ minutes) → RVC training (highest fidelity)
    |   |-- Yes (any length, budget) → ElevenLabs (production quality)
    |
    |-- No reference audio?
    |   |-- Need emotion control → IndexTTS-2 (8-emotion vectors)
    |   |-- Need multi-language → TTS Audio Suite (23 languages)
    |   |-- Need voice design → ElevenLabs Voice Design (describe voice)
    |   |-- Quick prototype → Any TTS with default voice
    |
    |-- Need multi-speaker dialog?
    |   |-- Chatterbox (4 voices) or TTS Audio Suite (character switching)
    |
    |-- Need lip-sync?
    |   |-- Best accuracy → Wav2Lip + CodeFormer
    |   |-- Need head movement → SadTalker
    |   |-- Full expression control → LivePortrait
    |   |-- Unlimited length → InfiniteTalk

[laugh] [chuckle] [sigh] [gasp] [cough] [clear throat]
[whisper] [excited] [sad] [angry] [surprised]

voice:
  cloned: true
  model: "chatterbox"
  sample_file: "references/voice_sample.wav"
  settings:
    exaggeration: 1.2
    default_emotion: "neutral"
  notes: "Warm, confident tone. Slight Italian-American undertones."

[Sage] Hello! *laughs* I've been looking forward to this.
[pause:0.5s]
[Alex] [excited] Same here! Let's dive right in.
[Sage] [whisper] But first, I need to tell you something...

# Convert to mono 24kHz WAV, normalized
ffmpeg -i input.wav -ac 1 -ar 24000 -af "loudnorm=I=-16:TP=-3" output.wav

# Trim silence from start/end
ffmpeg -i input.wav -af "silenceremove=start_periods=1:start_threshold=-50dB,areverse,silenceremove=start_periods=1:start_threshold=-50dB,areverse" trimmed.wav

# Concatenate segments
ffmpeg -f concat -safe 0 -i filelist.txt -c copy combined.wav

wav2lip_model: "wav2lip_gan.pth"  # Better than wav2lip.pth
face_detect_batch: 16
nosmooth: false
pad_bottom: 10

preprocess: "full"     # Better for novel faces
enhancer: "gfpgan"
pose_style: 10-20      # Natural conversation range

lip_zero: 0.03         # Reduces unnatural lip movement
stitching: true        # Seamless face blending

1. [Text] → Chatterbox/F5-TTS → audio.wav
2. [Character Image] + audio.wav → SadTalker → video.mp4
3. video.mp4 → GFPGAN/CodeFormer → final.mp4

1. [Text] → Chatterbox → audio.wav
2. [Character Image] → Wan I2V → base_video.mp4
   Prompt: "person talking, slight head movement, indoor"
3. base_video.mp4 + audio.wav → Wav2Lip → lipsync.mp4
4. lipsync.mp4 → FaceDetailer batch → enhanced.mp4
5. enhanced.mp4 → Color correct + Deflicker → final.mp4

1. Record driving video (actor performing lines)
2. [Text] → Voice Clone TTS → audio.wav
3. [Character Image] + driving.mp4 → LivePortrait → expression_video.mp4
4. expression_video.mp4 + audio.wav → Wav2Lip → lipsync.mp4
5. lipsync.mp4 → CodeFormer → final.mp4