Remove audio segments matching keyword definitions using transcription and FFmpeg.
npx skills add https://github.com/wlzh/skills --skill audiocut-keyword
Please help me install this Agent Skill. Skill: audiocut-keyword Source: https://github.com/wlzh/skills/tree/main/audiocut-keyword Command: npx skills add https://github.com/wlzh/skills --skill audiocut-keyword
This Skill automates the removal of undesired spoken segments from audio recordings by keyword-based detection and configurable buffers, cutting down manual editing time.
Use the audiocut-keyword skill to filter an audio file:
High-intent search queries and answers about installing and using this skill.
To automatically remove specific keywords from podcast audio, this skill uses FunASR transcription to detect spoken keywords and FFmpeg to trim the matching segments with configurable time buffers.
The best way to filter unwanted segments from audio recordings in batch is using keyword-driven detection that generates character-level timestamps and applies FFmpeg-based clipping to delete targeted spoken content.
Yes, FunASR supports Chinese keyword detection for audio editing by generating character-level transcription timestamps, allowing precise identification and removal of Chinese spoken segments from source audio.
You can configure time buffers when trimming audio around detected keywords through adjustable buffer settings in the keyword configuration file, allowing you to control how much surrounding audio is removed during clipping.
Yes, you can integrate optional voice changing into an audio editing workflow alongside keyword filtering, allowing you to modify speaker characteristics while simultaneously removing undesired spoken segments detected by transcription.
Keyword-based audio filtering requires character-level transcription timestamps because they provide the precise start and end points of spoken words, enabling FFmpeg to accurately clip segments without cutting partial words or phrases.
2670044605Filter audio segments containing configured keywords using FunASR transcripts and FFmpeg clipping.
onesmartguyAutomate FFmpeg batch audio processing with loudnorm and filter_complex mixing.
pproencaEnhances degraded audio and transcribes speech using FFmpeg, SoX, Whisper, and RNNoise.
davduncGenerate word-level transcripts, classify segments, and apply ffmpeg edits with crossfades to clean audio recordings.
