Transcribe local audio/video via Volcengine ASR and generate timestamped transcripts, SRT subtitles, and rough-cut MP4s.
npx skills add https://github.com/mcncarl/yichen-skills --skill volc-asr
Please help me install this Agent Skill. Skill: volc-asr Source: https://github.com/mcncarl/yichen-skills/tree/main/volc-asr Command: npx skills add https://github.com/mcncarl/yichen-skills --skill volc-asr
This skill enables automatic transcription of local audio/video files using Volcengine ASR and provides an automated rough-cut process to remove filler, pauses, and repetitions, producing editable transcripts and trimmed video.
Transcribe a local video or audio file and generate a timestamped transcript, SRT subtitles, and a rough-cut MP4 for editing.
High-intent search queries and answers about installing and using this skill.
You can transcribe local audio and video files with timestamps by using Volcengine ASR, which automatically processes the media to generate SRT-ready subtitles and structured transcripts.
Automating rough-cut editing for long-form interviews involves analyzing ASR transcripts to detect and remove repetitions, silences, and filler content, producing a clean MP4 and an editable text file.
Yes, the transcription task supports resumable queries and caching, allowing you to resume interrupted ASR processes without losing progress.
Yes, Volcengine ASR transcription requires environment-based app selection and token management to authenticate and route your local media processing requests.
Automated rough-cut editing trims the video to remove filler and pauses, resulting in a clean rough-cut MP4 that retains the original media quality for further editing.
ASR transcription outputs timestamped transcripts and SRT-ready subtitle files, providing formats that integrate easily into video editing and publishing workflows.
imlewcConverts online or local videos to subtitles and generates AI summaries.
thejordanleopoldTranscribe audio, analyze frames, and export a Final Cut Pro XML rough cut.
different-aiTranscribe video speech, detect filler words and pauses, and generate FFmpeg cut commands with SRT subtitles.
buda-aiTranscribe audio and video into timestamped TXT, SRT, and JSON transcripts.
