Transcribe video audio into timestamped SRT, VTT, or JSON transcripts.
npx skills add https://github.com/akrindev/trimer-clip --skill video-transcriber
Please help me install this Agent Skill. Skill: video-transcriber Source: https://github.com/akrindev/trimer-clip/tree/main/skills/video-transcriber Command: npx skills add https://github.com/akrindev/trimer-clip --skill video-transcriber
Transcribe video audio into accurate, timestamped transcripts for captions, searchability, and content analysis, reducing manual transcription effort.
Transcribe a video file using the supported backends and export the results as SRT, VTT, or JSON.
High-intent search queries and answers about installing and using this skill.
Generate timestamped transcripts with speaker diarization by processing video files through backends like Whisper local, OpenAI API, Google Speech-to-Text, or Gemini to identify speakers and export SRT, VTT, or JSON captions.
The best way to add subtitles is by running video audio through multiple speech-to-text backends like Whisper or Gemini, which transcribe the speech and export timestamped subtitle files in SRT or VTT formats for editing workflows.
Yes, video transcription requires FFmpeg to extract and process audio from video files before applying speech-to-text backends, speaker diarization, and emotion detection to generate accurate timestamped text outputs.
Yes, you can apply optional emotion detection during audio transcription alongside speaker diarization, exporting analyzed results as structured JSON, SRT, or VTT caption files.
Backends like local Whisper, OpenAI API, Google Speech-to-Text, and Gemini offer flexible video caption generation, varying in API key requirements and processing approaches while outputting standard SRT, VTT, or JSON transcript formats.
TeamWiseFlowIdentify and clip high-value video moments using ASR transcription and text analysis.
damionrashfordTranscribe audio or video into SRT/VTT subtitles with word timestamps.
video-production-buddyDownload video, audio, and subtitles from over 1000 public sites via yt-dlp.
papachongTranscribe audio files to text locally using the Whisper CLI.
