Generate waveform images and output crop_spec JSON for silence detection.
npx skills add https://github.com/theSamPadilla/montaj --skill waveform-silence
Please help me install this Agent Skill. Skill: waveform-silence Source: https://github.com/theSamPadilla/montaj/tree/main/skills/waveform-silence Command: npx skills add https://github.com/theSamPadilla/montaj --skill waveform-silence
This Skill helps editors and agents detect silences in audio/video clips when fixed dB threshold methods fail due to inconsistent background noise, room changes, or intermittent ambient sounds, producing reliable trim specifications per clip.
Use waveform-silence to generate waveform images for each clip, visually identify silences relative to each clip's noise floor, and output crop_spec trim specs for cropping.
High-intent search queries and answers about installing and using this skill.
Detect silence in audio with variable background noise by generating waveform images per clip to establish a visual noise floor baseline. This method identifies silence regions reliably when fixed dB threshold methods fail due to intermittent ambient sounds or changing room acoustics.
The best way to trim silent gaps from multi-clip recordings is to analyze 1920px-wide waveform images per clip. This visual analysis merges short gaps, timestamps boundaries to 0.1s precision, and outputs crop_spec JSON keeps for downstream cropping.
Visual waveform silence detection works by analyzing chunked waveform images to establish a per-clip noise floor rather than applying a global fixed threshold. It distinguishes sustained speech from flat noise regions and avoids cutting transient spikes or mid-word dips.
Yes, you can use visual silence detection for clips with fans or music in the background. It recovers clean speech regions by determining a noise floor baseline per clip, making it suitable for multi-clip recordings where mic placement changes or ambient sounds vary.
Output trim specifications after identifying silence regions by converting visual boundaries into timestamped keeps and calling crop_spec. This produces trimmed spec JSON designed for downstream editing steps like rm_fillers or concat in multi-clip montages.
levanminhducAnalyze local and YouTube videos with the Gemini API for summarization and Q&A.
theSamPadillaSelect the best take per script section and generate cropped trim spec paths.
theSamPadillaGenerate Montaj workflow JSON files with dependency waves for parallel execution.
yahav123147Install and configure the Silence Cutter CEP extension for Adobe Premiere Pro.
