From media
AI audio enhancement - Auphonic, Adobe Speech, noise removal, leveling, podcast polish
npx claudepluginhub willsigmon/sigstack --plugin mediaThis skill is limited to using the following tools:
Polish podcast and voice audio with AI enhancement tools.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Automates semantic versioning and release workflow for Claude Code plugins: bumps versions in package.json, marketplace.json, plugin.json; verifies builds; creates git tags, GitHub releases, changelogs.
Polish podcast and voice audio with AI enhancement tools.
curl -X POST https://auphonic.com/api/simple/productions.json \
-u "user:pass" \
-F "input_file=@episode.mp3" \
-F "output_basename=episode-enhanced" \
-F "algorithms=loudness,leveler,denoise"
import auphonic
client = auphonic.Client(username="...", password="...")
production = client.create_production(
input_file="episode.mp3",
algorithms=["loudness", "leveler", "denoise", "filtering"],
output_files=[{
"format": "mp3",
"bitrate": 128
}]
)
production.start()
1. Noise reduction (remove constant noise)
2. De-reverb (reduce room echo)
3. Leveling (balance speakers)
4. Compression (even out volume)
5. Loudness normalization (hit target LUFS)
# Get noise profile
ffmpeg -i input.mp3 -af "silencedetect=n=-30dB:d=0.5" -f null -
# Apply noise reduction
ffmpeg -i input.mp3 \
-af "highpass=f=80,lowpass=f=12000,afftdn=nf=-20" \
output.mp3
# Normalize + noise reduce
sox input.mp3 output.mp3 \
norm -1 \
noisered noise.prof 0.21
# Auphonic batch
for file in audio_files:
production = client.create_production(
input_file=file,
algorithms=["loudness", "leveler"]
)
production.start()
Use when: Podcast polish, voice clarity, noise removal, loudness normalization