evo-dubbing

Multilingual Dubbing Skill

This skill provides a complete pipeline for dubbing video from one language to another using neural TTS, with broadcast-standard audio output.

Capabilities

• Parse SRT subtitle files for timing windows and dialogue text
• Synthesize speech using Kokoro TTS with language-appropriate voices
• Two-step duration matching: Kokoro speed parameter + rate adjustment
• Normalize audio to ITU-R BS.1770-4 target (-23 LUFS per EBU R128)
• Mux dubbed audio into video container (configurable sample rate, mono)
• Generate structured JSON report with per-segment alignment metrics
• Validate output quality with UTMOS scoring

Quick Start

The caller must supply paths to the input files and output directory. All paths are runtime arguments with no defaults.

import sys
sys.path.insert(0, '/app/environment/skills/evo-dubbing/scripts')
from pipeline import run_dubbing_pipeline
from validator import validate_dubbing_output

# Discover input paths from the task environment at runtime.
# These are illustrative variable names - adapt to actual task layout.
video_path = '<path-to-input-video>'         # e.g. /root/input.mp4
segments_srt = '<path-to-segments-srt>'       # defines speech time windows
source_text_srt = '<path-to-source-text-srt>' # original language dialogue
target_text_srt = '<path-to-target-text-srt>' # reference translation
target_lang_file = '<path-to-target-lang>'    # file containing ISO 639-1 code
out_dir = '<output-directory>'                # e.g. /outputs

# Run the full pipeline
report = run_dubbing_pipeline(
    video_path=video_path,
    segments_srt_path=segments_srt,
    source_text_srt_path=source_text_srt,
    target_text_srt_path=target_text_srt,
    target_language_path=target_lang_file,
    output_dir=out_dir,
    target_sr=48000,       # broadcast standard
    target_channels=1,     # mono
    target_lufs=-23.0      # EBU R128
)

# Validate all outputs
passed, issues = validate_dubbing_output(out_dir)
if passed:
    print("All validations passed!")
else:
    for issue in issues:
        print(f"ISSUE: {issue}")