Transcribes YouTube video content using available transcripts or audio transcription.
This tool offers APIs to fetch and transcribe YouTube video content, supporting both REST API (Flask) and MCP server implementations. It automatically detects available transcripts in multiple languages (English and Vietnamese), and falls back to audio transcription using Whisper when transcripts are unavailable. It provides features for language detection, temporary file cleanup, and progress reporting, ensuring efficient and accurate transcript generation.
Key Features
01Provides progress reporting for long-running transcription operations.
02Automatically detects the language of the video.
03Fetches YouTube video transcripts in multiple languages.
040 GitHub stars
05Supports REST API (Flask) and MCP server interfaces.
06Uses Whisper for audio transcription when transcripts are unavailable.
Use Cases
01Creating accessible content for hearing-impaired viewers.
