What transcription providers does Vidscribe offer?

Vidscribe supports five ASR providers: Volcengine, OpenAI (Whisper API), Aliyun, Deepgram, and an offline local faster-whisper model, offering flexibility in quality, speed, and cost.

Which video platforms does Vidscribe support?

Vidscribe supports over 1000 video platforms, including popular ones like YouTube, Bilibili, TikTok, Vimeo, and Twitter/X, by leveraging the powerful yt-dlp library.

Can Vidscribe transcribe videos in languages other than English?

Yes, Vidscribe offers robust multilingual transcription capabilities, supporting Chinese, English, Japanese, and over 50 other languages, depending on the selected ASR provider.

How does Vidscribe integrate with AI assistants like Claude or Cursor?

It integrates in two ways: as an MCP Server for clients like Claude Desktop and Cursor, or as an Agent Skill for AI assistants such as Cursor, Windsurf, and Codex. This allows your AI to directly transcribe videos.

What is Vidscribe and its primary function?

Vidscribe is a versatile tool that transcribes any video URL into text. It integrates with AI assistants as an MCP Server or Agent Skill, and can also be used as a standalone command-line interface (CLI) tool.

Vidscribe

Name: Vidscribe
Author: XFWang522

•

Transcribe any video URL to text using a variety of ASR providers and integrate with AI assistants.

Vidscribe

•

Transcribe any video URL to text using a variety of ASR providers and integrate with AI assistants.

Vidscribe empowers AI coding assistants and CLI users to effortlessly convert any video URL into a text transcript. Supporting over 1000 platforms like YouTube, Bilibili, and TikTok via yt-dlp, it offers a choice of five ASR providers, including OpenAI Whisper and a local offline option, ensuring flexibility in terms of quality, speed, and cost. Whether integrated as an MCP server for clients like Claude Desktop and Cursor, or as an Agent Skill for intelligent assistants, Vidscribe streamlines the process of extracting textual content from spoken word in videos, making information accessible for analysis or further AI processing.

主な機能

01Functions as an Agent Skill for AI assistants like Cursor, Windsurf, and Codex

02Offers multilingual transcription and an offline processing option

03Transcribes videos from 1000+ sites (Bilibili, YouTube, TikTok, etc.) via yt-dlp

04Integrates as an MCP Server for Claude Desktop, Cursor, and other MCP clients

05Supports 5 ASR providers (Volcengine, OpenAI, Aliyun, Deepgram, Local faster-whisper) with auto-detection

061 GitHub stars

ユースケース

01Quickly generating text transcripts from online video content for analysis, content creation, or accessibility

02Equipping AI coding assistants with video transcription capabilities for advanced context processing

03Converting speech from videos into text for data science, machine learning, or research purposes