video-to-text-openai

Transcribe video or audio into text and SRT subtitles using yt-dlp and OpenAI Whisper.

40|6|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/0xmariowu/Autosearch --skill video-to-text-openai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-to-text-openai
Source: https://github.com/0xmariowu/Autosearch/tree/main/autosearch/skills/tools/video-to-text-openai
Command: npx skills add https://github.com/0xmariowu/Autosearch --skill video-to-text-openai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe video or audio content into text and SRT subtitles for easier analysis, indexing, and accessibility.

Core Features & Use Cases

  • Transcribes video or audio from URLs or local files using yt-dlp for extraction and OpenAI Whisper for transcription, returning raw text and subtitle data.
  • Supports multiple sources (YouTube, Bilibili, Douyin, Xiaoyuzhou, and local media) and is suitable for podcast transcription, lecture captions, and media archival.

Quick Start

Instruct the system to transcribe the provided media URL or local file into text and SRT subtitles.

Frequently Asked Questions about video-to-text-openai

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

FAQPage Schema
How do I transcribe a YouTube video to text and generate SRT subtitles?

To transcribe YouTube video to text and generate SRT subtitles, this skill extracts media via yt-dlp and processes audio via OpenAI Whisper, returning raw text and SRT subtitle data.

Do I need an OpenAI API key to transcribe audio and video files?

Yes, you need an OPENAI_API_KEY to transcribe audio and video files, as the skill implements transcription via OpenAI Whisper and includes structured error handling for API rate limits and failures.

Can I transcribe local media files or do I need a URL from Bilibili and Douyin?

You can transcribe local media files directly without a URL, and the tool also supports extracting and transcribing video content from Bilibili, Douyin, Xiaoyuzhou, and YouTube sources.

What is the best way to convert podcast audio to text for lecture captions?

The best way to convert podcast audio to text for lecture captions is using yt-dlp for media extraction and OpenAI Whisper for transcription, which outputs structured raw text and SRT subtitles.

Why does video-to-text transcription fail when hitting OpenAI rate limits?

Video-to-text transcription fails on rate limits because the skill relies on the OpenAI Whisper API, but it provides structured error handling to manage API failures and rate limit exceptions gracefully.