MCP Video Digest logo

MCP Video Digest

by R-lz

MCP Video Digest is a video content processing service that extracts audio from videos from platforms like YouTube, Bilibili, and TikTok and converts it to text. It supports multiple transcription service providers, offering flexibility in service selection based on configured API keys.

View on GitHub

Last updated: N/A

What is MCP Video Digest?

MCP Video Digest is a service designed to extract and summarize video content. It downloads audio from various video platforms, transcribes it using multiple transcription services (Deepgram, Gladia, Speechmatics, AssemblyAI), and provides the resulting text.

How to use MCP Video Digest?

  1. Clone the repository. 2. Configure API keys in the .env file. 3. Install dependencies using uv pip install -e .. 4. Start the service using uv run src/main.py. 5. Use the client library to call the get_video_content method with a video URL.

Key features of MCP Video Digest

  • Supports downloading and audio extraction from over 1000 websites.

  • Supports multiple transcription service providers: Deepgram, Gladia, Speechmatics, AssemblyAI.

  • Automatically selects the best service based on available API keys.

  • Asynchronous processing for improved concurrency.

  • Complete error handling and logging.

  • Supports speaker diarization.

Use cases of MCP Video Digest

  • Automatically generate transcripts for YouTube videos.

  • Summarize lectures or presentations from video recordings.

  • Create searchable archives of video content.

  • Analyze spoken content in videos for sentiment or keywords.

FAQ from MCP Video Digest

What API keys do I need?

You need API keys for at least one of the supported transcription services: Deepgram, Gladia, Speechmatics, or AssemblyAI. Deepgram is recommended for Chinese content.

How do I choose which transcription service to use?

The service automatically selects the best available service based on the configured API keys and a predefined priority order (Deepgram > Gladia > Speechmatics > AssemblyAI).

How do I install the dependencies?

Use uv pip install -e . to install the required dependencies. It is recommended to use uv for faster dependency installation.

How do I run the tests?

Run uv run test.py or python test.py to execute the test suite.

Where can I find the free tiers for STT services?

Speechmatics offers 8 hours/month, Gladia offers 10 hours/month, AssemblyAI offers $50 free credit, and Deepgram offers $200 free credit. See their respective pricing pages for more details.