skills.rest
gilinachum
gilinachumCOMMUNITY
Explore all skills by this author →
GitHub

transcription-workflow

Transcribe audio and video files into structured content with summaries, chapters, and video plans.

3|Updated Apr 23, 2026
Search Tags:#summarization#video#transcription#audio#chapters#hebrew#aws transcribe
One-click install
npx skills add https://github.com/gilinachum/youtube-storyteller --skill transcription-workflow-gilinachum
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcription-workflow
Source: https://github.com/gilinachum/youtube-storyteller/tree/main/agent/knowledge/transcription-workflow
Command: npx skills add https://github.com/gilinachum/youtube-storyteller --skill transcription-workflow-gilinachum

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning raw audio or video recordings into usable written content requires manual listening, note-taking, and structuring, which is slow and error-prone for creators working with Hebrew or English recordings. ## Core Features & Use Cases - Async Transcription: Starts AWS Transcribe jobs on uploaded .mp3, .mp4, .webm, .wav, or .m4a files and retrieves results without blocking the conversation. - Post-Processing Options: Cleans up filler words, extracts key topics, creates chapter markers, and summarizes main points from the transcript. - Video Plan Conversion: Converts a spoken recording into a structured YouTube video script outline. - Use Case: A creator uploads a 30-minute Hebrew voice memo of video ideas; the Skill transcribes it, then produces a cleaned summary with chapter markers and a downloadable transcript link. ## Quick Start Upload an audio file and ask the assistant to transcribe it and turn the result into a video plan with chapters.

Frequently Asked Questions about transcription-workflow

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe an audio file to text?▼

Upload an .mp3, .mp4, .webm, .wav, or .m4a file and the Skill starts an AWS Transcribe job on the file's S3 key. Transcription takes 1-5 minutes depending on length, and you are notified when the result is ready.

What can I do with a transcript after transcription?▼

The transcript can be cleaned of filler words, summarized into bullet points, segmented into chapters with titles, or converted into a YouTube video plan. The Skill asks which post-processing option you want after transcription completes.

Does the transcription support Hebrew audio?▼

Yes, AWS Transcribe auto-detects the language and handles Hebrew transcription with good quality. Technical terms may need manual fixes, so reviewing the output for specialized vocabulary is recommended.

Why is my transcription taking so long to complete?▼

Transcription is asynchronous and typically takes 1-5 minutes depending on file length. The conversation is not blocked while the job runs, and results are retrieved via the pending jobs list once processing finishes.

What are the limitations of the transcript output format?▼

The current implementation returns plain text without timestamps, so chapter markers are inferred from content rather than precise timecodes. Files must also reside in the session's uploads folder on S3 to be processed.

Related Skills

Explore More Content & Communication Skills→
ai-enhanced-engineerai-enhanced-engineer
3

mobile-video-upload

Automate mobile video uploads with resumable uploads and on-device compression.

Official
Intermediate
JlsilesJlsiles

retention-editing

Guide YouTube editors on pacing, pattern interrupts, and hook alignment.

Community
Advanced
xtrm-devxtrm-dev
4

last30days

Research recent discussions across social platforms and the web over 30 days.

Official
Advanced
FelixRauchFelixRauch

speech-recognition

Transcribe live microphone input and audio files via iOS Speech APIs.

Community
Intermediate