---
title: "video-to-text"
description: "Extract transcript text from videos (TikTok, YouTube, Instagram, X, any URL) or local video files, fully local, no API keys. Ships scripts/vxtract.py: yt-dlp download + ffmpeg audio extraction + faster-whisper transcript"
canonical: https://agentpluginsdirectory.com/plugins/video-to-text
last-updated: 2026-11-07
---

# video-to-text
Extract transcript text from videos (TikTok, YouTube, Instagram, X, any URL) or local video files, fully local, no API keys. Ships scripts/vxtract.py: yt-dlp download + ffmpeg audio extraction + faster-whisper transcription (Spanish/English/auto, CPU or CUDA) with.txt/.md/.srt output. Alternative to cloud transcription services.
- Slug: video-to-text
- Publisher: Antonio Gómez
- Repository: https://github.com/aintoniodev/autoskilling
- Manifest: video-to-text/plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): creative-media
- Skills: 1 (video-to-text)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-08-06
- Repository last pushed: 2026-10-30
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/video-to-text
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What video-to-text does, in the publisher's words

Extract transcript text from videos (TikTok, YouTube, Instagram, X, any URL) or local video files, fully local, no API keys.

Engine: yt-dlp (download) + ffmpeg (audio) + faster-whisper (STT).

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/aintoniodev/autoskilling/HEAD/video-to-text/README.md

## Skills

- video-to-text: Extract transcript text from videos, TikTok, YouTube, Instagram, X, any URL, or local video files, fully local with no API keys. EN: 'transcribe this video', 'extract text/subtitles from video', 'video to text'; ES: 'parsear texto de video', 'transcribir este video', 'sacar el texto/subtítulos de…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.