메뉴
FFmpeg audio processing, batch editing, normalization, mixing, and automated audio production workflows. Use when processing audio at scale, automating editing tasks, or building audio pipelines.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Debug and troubleshoot ElevenLabs conversational AI agents and Twilio calls. Use when diagnosing agent issues, analyzing failed calls, troubleshooting audio problems, investigating conversation breakdowns, reviewing error logs, or optimizing underperforming agents. Includes transcript analysis, error diagnosis, and performance troubleshooting.
Optimize ElevenLabs conversational AI agents for real estate applications. Use when creating new agents, improving conversation quality, selecting voices, engineering system prompts, configuring agent parameters, or analyzing agent performance metrics. Includes voice selection, model tuning, prompt engineering, and A/B testing strategies.
ElevenLabs voice cloning techniques, audio quality requirements, recording best practices, and training data optimization for professional-quality voice clones. Use when creating custom voices, cloning voices, or optimizing voice clone quality.
Sound effect sourcing from Adobe Audition, Freesound, ElevenLabs text-to-sound-effects, and audio library management for professional productions. Use when adding sound effects, building audio libraries, or creating immersive soundscapes.
Advanced text-to-speech optimization with expressional tone guides, natural speech patterns, prosody control, and human-like conversation techniques to create authentic-sounding AI voices. Use when generating natural speech, creating engaging content, or producing professional voiceovers.
Create production-ready ASP.NET Core Minimal API projects with async patterns, dependency injection, and comprehensive error handling. Use when building new .NET API applications or setting up backend API projects with .NET 8+.
| name | audio-editing-automation |
| description | FFmpeg audio processing, batch editing, normalization, mixing, and automated audio production workflows. Use when processing audio at scale, automating editing tasks, or building audio pipelines. |
ffmpeg -i input.mp4 -vn -acodec copy audio.aac
# -vn: no video
# -acodec copy: no re-encoding
# WAV to MP3
ffmpeg -i input.wav -c:a libmp3lame -b:a 192k output.mp3
# MP3 to AAC
ffmpeg -i input.mp3 -c:a aac -b:a 192k output.m4a
# Increase volume by 10dB
ffmpeg -i input.mp3 -af "volume=10dB" output.mp3
# Normalize using loudnorm filter
ffmpeg -i input.wav -af "loudnorm=I=-16:TP=-1.5:LRA=11" output.wav
# Mix two audio files
ffmpeg -i voice.mp3 -i music.mp3 -filter_complex amix=inputs=2:duration=longest output.mp3
# Voice + background music (ducking)
ffmpeg -i voice.mp3 -i music.mp3 -filter_complex \
"[1:a]volume=0.3[bg];[0:a][bg]amix=inputs=2:duration=first" output.mp3
import subprocess
from pathlib import Path
def normalize_audio_batch(input_dir, output_dir):
for audio in Path(input_dir).glob("*.mp3"):
output = Path(output_dir) / audio.name
subprocess.run([
'ffmpeg', '-i', str(audio),
'-af', 'loudnorm=I=-16:TP=-1.5',
str(output)
])
Format: MP3
Bitrate: 128-192kbps
Sample Rate: 44.1kHz
Loudness: -16 LUFS
Peak: -1dB
Format: MP3, 192kbps CBR
Sample Rate: 44.1kHz
Peak: -3dB
RMS: -18dB to -23dB
Noise Floor: -60dB
Format: AAC
Bitrate: 192kbps
Sample Rate: 48kHz
Loudness: -14 LUFS
def audio_production_pipeline(voice_file, music_file):
# 1. Normalize voice
normalize_audio(voice_file, 'voice_normalized.mp3')
# 2. Mix with music
mix_audio('voice_normalized.mp3', music_file, 'mixed.mp3')
# 3. Final loudness normalization
final_normalize('mixed.mp3', 'final.mp3', target_lufs=-16)
# 4. Export for platforms
export_for_podcast('final.mp3')
export_for_youtube('final.mp3')