Deep Transcribe
What is Deep Transcribe
Deep-transcribe is a tool that allows users to take video or audio URLs, such as those from YouTube, download and cache them, and perform a comprehensive transcription. This includes full transcription, speaker identification, adding sections, timestamps, annotations, and frame captures.
Use cases
Use cases for deep-transcribe include creating transcripts for educational videos, generating subtitles for media content, conducting interviews with speaker identification, and enhancing accessibility for hearing-impaired users.
How to use
To use deep-transcribe, set up your API keys for Deepgram and Anthropic in the ‘env.template’ file. Install the tool using ‘uv tool install --upgrade deep-transcribe’. Then, you can transcribe a video by running commands like ‘deep-transcribe transcribe
Key features
Key features of deep-transcribe include: full transcription, speaker identification, sectioning, timestamping, annotation capabilities, and the ability to insert frame captures. It is built on the kash framework and its media handling tools.
Where to use
Deep-transcribe can be used in various fields such as education, media analysis, content creation, and accessibility services, where detailed transcriptions and annotations of audio or video content are required.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Deep Transcribe
Deep-transcribe is a tool that allows users to take video or audio URLs, such as those from YouTube, download and cache them, and perform a comprehensive transcription. This includes full transcription, speaker identification, adding sections, timestamps, annotations, and frame captures.
Use cases
Use cases for deep-transcribe include creating transcripts for educational videos, generating subtitles for media content, conducting interviews with speaker identification, and enhancing accessibility for hearing-impaired users.
How to use
To use deep-transcribe, set up your API keys for Deepgram and Anthropic in the ‘env.template’ file. Install the tool using ‘uv tool install --upgrade deep-transcribe’. Then, you can transcribe a video by running commands like ‘deep-transcribe transcribe
Key features
Key features of deep-transcribe include: full transcription, speaker identification, sectioning, timestamping, annotation capabilities, and the ability to insert frame captures. It is built on the kash framework and its media handling tools.
Where to use
Deep-transcribe can be used in various fields such as education, media analysis, content creation, and accessibility services, where detailed transcriptions and annotations of audio or video content are required.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
deep-transcribe
Take a video or audio URL (such as YouTube), download and cache it, and perform a “deep
transcription” of it, including full transcription, identifying speakers, adding
sections, timestamps, and annotations, and inserting frame captures.
By default this needs API keys for Deepgram and Anthropic (Claude).
This is built on kash and its
kash-media kit of tools for handling videos.
Usage
See the env.template to set up DEEPGRAM_API_KEY and ANTHROPIC_API_KEY.
uv tool install --upgrade deep-transcribe
# Pick a YouTube video, and do a basic, formatted, or fully annotated transcription:
deep-transcribe transcribe https://www.youtube.com/watch?v=ihaB8AFOhZo
deep-transcribe transcribe_format https://www.youtube.com/watch?v=ihaB8AFOhZo
deep-transcribe transcribe_annotate https://www.youtube.com/watch?v=ihaB8AFOhZo
Results will be in the ./transcriptions directory.
To run as an MCP server:
# In stdio mode:
deep-transcribe mcp
# In SSE mode at 127.0.0.1:4440:
deep-transcribe mcp --sse
Or for Claude Desktop, a config like this should work (adjusted to use your appropriate
home folder):
To debug MCP logs:
deep_transcribe mcp --logs
Project Docs
For how to install uv and Python, see installation.md.
For development workflows, see development.md.
For instructions on publishing to PyPI, see publishing.md.
This project was built from
simple-modern-uv.
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
