skills.rest
GeneralReasoning
GeneralReasoningOFFICIAL
Explore all skills by this author →
Website𝕏@GenReasoningGitHub

speech-to-text

Transcribes video and audio files into timestamped text using a local Whisper model.

4|Updated Feb 22, 2026
Search Tags:#python#video#whisper#timestamps#speech-to-text#audio-processing#offline-transcription
One-click install
npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill speech-to-text-generalreasoning
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/GeneralReasoning/env-skillsbench/tree/main/video-tutorial-indexer/environment/skills/speech-to-text
Command: npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill speech-to-text-generalreasoning

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper, and includes scripts (resource) components.

What problem does it solve?

Transcribe video and audio locally into timestamped text, preserving privacy and avoiding cloud APIs.

Core Features & Use Cases

  • Local offline transcription using Whisper with a tiny model
  • Output with timestamped segments suitable for captions, transcripts, or searchable logs
  • Supports both video and audio inputs and can emit plain text or JSON transcripts

Quick Start

Run the transcribe.py script on your video file to generate a timestamped transcript using the pre-installed Whisper tiny model.

Frequently Asked Questions about speech-to-text

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

FAQPage Schema
How do I transcribe a video to text with timestamps locally?▼

You can transcribe video to text with timestamps locally by running the transcribe.py script, which processes your file using a pre-installed Whisper tiny model to output timestamped segments.

Can I get JSON transcripts from audio files using offline transcription?▼

Yes, offline transcription supports both video and audio inputs, allowing you to emit timestamped transcripts in either plain text or JSON format.

Do I need a cloud API to convert speech to text for privacy-preserving media archiving?▼

No, you do not need a cloud API for privacy-preserving media archiving. This local Whisper model processes speech-to-text conversion entirely offline.

What is the best way to generate searchable logs from educational video tutorials?▼

The best way to generate searchable logs from educational video tutorials is using offline transcription, which produces timestamped text segments suitable for searchable archives.

Does offline speech-to-text work with Python for software tutorial transcription?▼

Yes, offline speech-to-text works with Python by running a script that requires a local Whisper model and a Python runtime to transcribe software tutorials.

What are the limitations of using a Whisper tiny model for local transcription?▼

Using the Whisper tiny model for local transcription requires a Python runtime environment and outputs segments with start/end timestamps, limiting processing to pre-recorded files rather than real-time streams.

Related Skills

Explore More Software Engineering Skills→
geezerrrrgeezerrrr
117

openai-whisper

Transcribe audio and video files into text or SRT subtitles locally with Whisper CLI.

Community
Basic
XiaSanwXiaSanw
2

youtube-transcript

Extract YouTube video transcripts with optional timestamps from URLs.

Community
Intermediate
dislerdisler
1.5k

Video Processor

Extracts audio, converts video to MP4 or WebM, and transcribes with Whisper via Python CLI.

Community
Advanced
adbertramadbertram
3

whisper-cli

Transcribe local audio and video files into timestamped JSON transcripts using whisper.cpp.

Community
Intermediate