evo-dubbing-audio-processing
SkillSearchHandles audio resampling, loudness normalization per ITU-R BS.1770-4, and LUFS measurement for TTS segments to ensure broadcast-quality output.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the evo-dubbing-audio-processing skill
What this skill tells your AI
The instructions your AI receives, as published by openlair/openskill in tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-audio-processing/SKILL.md and read by ahel’s review.
Resamples audio from Kokoro's 24kHz to 48kHz and applies ITU-R BS.1770-4 loudness normalization.
Key Functions
resample_audio(audio, orig_sr, target_sr)- Resample numpy arraymeasure_lufs(audio_path)- Measure LUFS using FFmpeg loudnorm filter (pass 1)normalize_loudness(audio_path, output_path, target_lufs)- Two-pass loudness normalizationprocess_segment_audio(input_path, output_path, target_sr, target_lufs)- Full processing pipeline
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-dubbing-audio-processing/scripts')
from utils import process_segment_audio, measure_lufs
process_segment_audio('/outputs/tts_segments/seg_0.wav', '/outputs/tts_segments/seg_0.wav', 48000, -23.0)
lufs = measure_lufs('/outputs/tts_segments/seg_0.wav')
Technical Details
- ITU-R BS.1770-4 standard for loudness measurement
- Target LUFS: -23.0 for broadcast standard
- Two-pass FFmpeg loudnorm: measure first, then normalize with linear=true
- Resample from 24kHz to 48kHz using scipy.signal.resample_poly
- Output: 48kHz mono WAV PCM_16
Signals
- GitHub stars
- 89
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
evo-dubbing-audio-processing- Source
- github.com/openlair/openskill