biliscribe
by mcp-server-summary
Biliscribe is a MCP Server that extracts and formats Bilibili video content into structured text, optimized for LLM processing and analysis. It converts Bilibili videos into text for summarization by large language models.
Last updated: N/A
What is biliscribe?
Biliscribe is an MCP Server designed to extract audio from Bilibili videos, transcribe it, and format the resulting text in a structured manner suitable for processing and analysis by Large Language Models (LLMs).
How to use biliscribe?
To use Biliscribe, first install the mcp-server-biliscribe package using uvx. Ensure that ffmpeg is callable from your shell environment. Configure the necessary environment variables for Cloudflare R2 access and Replicate API Key. Then, run the server using either standard I/O or Server-Sent Events (SSE) protocol, configurable via the BILISCRIBE_SERVER_SSE environment variable.
Key features of biliscribe
Bilibili video transcription
Structured text output
Optimized for LLM processing
Cloudflare R2 storage integration
Replicate API integration (WhisperX)
Supports stdio and SSE communication protocols
Use cases of biliscribe
Summarizing Bilibili video content with LLMs
Analyzing Bilibili video transcripts for trends and insights
Creating searchable archives of Bilibili video content
Generating subtitles or closed captions for Bilibili videos
Automated content extraction from Bilibili videos
FAQ from biliscribe
What is ffmpeg and why is it required?
What is ffmpeg and why is it required?
ffmpeg is a free and open-source software project consisting of a large suite of libraries and programs for handling video, audio, and other multimedia files and streams. It is required for extracting audio from Bilibili videos.
What is Cloudflare R2 and why is it needed?
What is Cloudflare R2 and why is it needed?
Cloudflare R2 is a distributed object storage service. It is used to store the audio data extracted from Bilibili videos.
What is Replicate API and why is it needed?
What is Replicate API and why is it needed?
Replicate API provides access to machine learning models, including WhisperX. It is used for transcribing the audio data into text.
What environment variables are required?
What environment variables are required?
The required environment variables are: REPLICATE_API_TOKEN, S3_API_ENDPOINT, BUCKET_NAME, ACCESS_KEY, and SECRET_KEY.
How do I choose between stdio and SSE communication protocols?
How do I choose between stdio and SSE communication protocols?
The choice depends on your specific needs. stdio is the default and simpler to use. SSE allows for server-sent events, which can be useful for real-time updates or streaming data.