bilibili-to-text

Extracts text from Bilibili videos and subtitles using yt-dlp, ffmpeg, and faster-whisper ASR.

Updated May 27, 2026
One-click install
npx skills add https://github.com/RuifengFu/agent-skills --skill bilibili-to-text
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bilibili-to-text
Source: https://github.com/RuifengFu/agent-skills/tree/main/hermes/bilibili-to-text
Command: npx skills add https://github.com/RuifengFu/agent-skills --skill bilibili-to-text

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, ffmpeg, faster-whisper, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of extracting text from Bilibili videos and subtitles, making it easier to convert video content into written form.

Core Features & Use Cases

  • Video to Text: Extracts text from Bilibili videos, including automatic subtitle extraction and ASR (Automatic Speech Recognition) for videos without subtitles.
  • Subtitle Extraction: Retrieves subtitles from Bilibili videos, supporting both Bilibili's native subtitle format and other common subtitle formats.
  • Use Case: Ideal for content creators who need to transcribe video content for accessibility or for those who want to create text-based resources from video content.

Quick Start

Use the bilibili-to-text skill to transcribe the audio from the video 'BV1xxxxxx'.

Frequently Asked Questions about bilibili-to-text

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

FAQPage Schema
How do I extract text from a Bilibili video?

To extract text from a Bilibili video, this Skill uses yt-dlp to download the video, ffmpeg to extract audio, and faster-whisper for ASR. It can also retrieve native Bilibili subtitles directly when available.

Can I get subtitles from Bilibili videos without doing speech recognition?

Yes, subtitle extraction from Bilibili videos can retrieve native Bilibili subtitle formats directly. Automatic speech recognition via faster-whisper is only applied as a fallback for videos without existing subtitles.

Do I need to install yt-dlp and ffmpeg to convert Bilibili videos to text?

Yes, converting Bilibili videos to text requires yt-dlp for video downloading, ffmpeg for audio extraction, and Python with faster-whisper installed for automatic speech recognition.

What is the best way to transcribe Bilibili video audio for content creation?

The best way to transcribe Bilibili video audio is using an automated pipeline that downloads the video, extracts the audio track, and applies ASR. This Skill handles that workflow using faster-whisper to generate text output.

Does faster-whisper work well for extracting text from long Bilibili videos?

Faster-whisper is used for ASR to extract text from Bilibili video audio. While suitable for content creators and educators, processing long videos depends on your local hardware capabilities and available storage for the downloaded media.