Transforms raw audio files into polished podcasts via trimming, filler removal, and enhancement.
npx skills add https://github.com/enowdev/enowX-Skill --skill podcast-edit
Please help me install this Agent Skill. Skill: podcast-edit Source: https://github.com/enowdev/enowX-Skill/tree/main/skill/skills/podcast-edit Command: npx skills add https://github.com/enowdev/enowX-Skill --skill podcast-edit
This Skill automates the tedious, time-consuming process of editing raw podcast recordings, including trimming unwanted segments, removing filler words, and normalizing audio quality to industry standards.
Use the podcast-edit skill to process the raw audio file named recording.mp3 by removing all filler words and normalizing the loudness to podcast standards.
High-intent search queries and answers about installing and using this skill.
To remove filler words from podcast audio, this Skill uses AI-driven transcription to identify verbal tics like um and uh, then automatically cuts them to improve flow. It processes long-form recordings to enhance clarity without manual editing.
The best way to normalize loudness to podcast standards is applying professional-grade audio processing that targets -16 LUFS. This ensures consistent volume levels across the entire episode for broadcast-ready output.
Yes, you need an OpenAI API key to process and trim raw audio recordings. The Skill requires Whisper-based transcription for intelligent trimming and filler word detection, along with ffmpeg, ffprobe, and python3 dependencies.
While ffmpeg handles audio processing, AI-driven transcription detects and trims pre-show chatter from raw podcast files. The Skill combines Whisper-based analysis with ffmpeg to intelligently remove unwanted segments.
Audio enhancement techniques applied when editing podcasts include noise reduction, EQ, and loudness normalization to -16 LUFS. These professional-grade processes ensure consistent volume and remove distracting silences from the recording.
Yes, this audio normalization approach works on hour-long interview recordings. It operates on long-form audio files to improve clarity, remove silence, and ensure consistent loudness levels suitable for broadcast-ready episodes.
framerslabTranscribe audio and video files to text using OpenAI Whisper.
dkyazzentwatwaNormalize audio volume levels using peak, RMS, or LUFS methods.
JosiahSiegelAutomate audio encoding, normalization, and enhancement with FFmpeg.
BishopCodesTranscribe audio with word-level timestamps and remove filler words.
