Converts audio and video files into timestamped transcripts for TXT, JSON, SRT, and VTT.
npx skills add https://github.com/CoachSteff/superskills --skill transcriber
Please help me install this Agent Skill. Skill: transcriber Source: https://github.com/CoachSteff/superskills/tree/main/superskills/transcriber Command: npx skills add https://github.com/CoachSteff/superskills --skill transcriber
AI-powered transcription of audio and video recordings into accurate, timestamped text to enable quick search, editing, and repurposing.
Transcribe a file by calling transcribe_file('path/to/file.ext') to generate a transcript.
High-intent search queries and answers about installing and using this skill.
To convert audio to text with timestamps for multiple files, you can use batch processing to generate timestamped transcripts. This workflow supports single or multiple files and exports word-level timestamps across TXT, JSON, SRT, and VTT formats.
Yes, you need API keys for Whisper or AssemblyAI to transcribe video. The transcription workflow requires selecting one of these providers and configuring their respective API keys to process the audio or video recordings into text.
Yes, you can generate SRT and VTT subtitle files from audio recordings. The transcription process exports outputs in multiple formats including TXT, JSON, SRT, and VTT to support diverse downstream video editing and subtitling workflows.
The best way to extract quotes from audio for marketing is using batch transcription with optional quote discovery. This processes multiple files in a single run to convert speech into searchable text and identify notable quotes automatically.
Yes, batch audio transcription supports optional language detection and word-level timestamps. These features apply across both single-file and batch workflows, providing precise timing data for editable and searchable transcripts.
costiashTranscribe local videos and YouTube content into timestamped transcripts using gpt-4o-transcribe.
maxgent-aiTranscribe audio and video files with word-level timestamps using WhisperX.
Will-GoAutomate text-to-speech, transcription, and background removal for multimedia assets.
lemonlqfTranscribe and translate audio and video files into text or subtitles using the Whisper CLI.
