From claude-transcription
Remove long silences from an audio file using VAD (voice activity detection). Use when the user asks to truncate silence, remove gaps, trim pauses, or apply VAD to an audio recording.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin claude-transcriptionThis skill uses the workspace's default tool permissions.
Strip long silent regions from a recording before transcription.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Share bugs, ideas, or general feedback.
Strip long silent regions from a recording before transcription.
ffmpeg -i INPUT \
-af "silenceremove=start_periods=1:start_duration=0.5:start_threshold=-40dB:detection=peak,\
silenceremove=stop_periods=-1:stop_duration=1.0:stop_threshold=-40dB:detection=peak" \
OUTPUT
Thresholds tuned for speech. Expose --threshold-db and --min-silence params.
uv run --with silero-vad --with torch --with torchaudio python -c '...'
Use when ffmpeg leaves residual silence or when recording has low-volume speech.
<source_stem>.trimmed.<ext>