How do I trigger the transcription process?

Simply use the keyword 'TRANSCRIBE' in your Claude Code prompt, and the skill will automatically find and process the most recent audio file in your Downloads folder.

What audio formats does this skill support?

It supports a wide range of formats including MP3, M4A, WAV, FLAC, OGG, and WebM, as well as video formats like MP4 and MOV.

Is an API key required for this skill?

Yes, you must have an AssemblyAI API key set as an environment variable (ASSEMBLYAI_API_KEY) for the transcription service to function.

How does the speaker diarization work?

The skill uses AssemblyAI's speaker labels feature to distinguish between different voices and can even identify speakers by name if their identities are clear from the context.

Where are my transcripts stored?

Transcripts are automatically moved to a local archive in your home directory (~/.transcripts/) and sorted into subfolders like work, personal, or academic based on the content.

AssemblyAI Audio Transcription

Name: AssemblyAI Audio Transcription
Author: WarrenZhu050413

byWarrenZhu050413

•

生産性とワークフロー

Automates high-accuracy audio transcription and speaker diarization with intelligent file organization and summarization.

This skill provides a comprehensive workflow for transcribing audio and video files using AssemblyAI's advanced speech-to-text models. It automatically detects the latest media files in your downloads folder, applies speaker diarization to distinguish different voices, and uses AI to generate descriptive filenames based on the conversation's content. Beyond simple transcription, it intelligently archives documents into categorized directories—such as work, personal, or academic—and provides a structured post-transcription summary including identified speakers, key topics, and action items.

主な機能

01Advanced speaker diarization using Universal-3-Pro models

02Automatic detection of the latest local audio and video files

035 GitHub stars

04Categorized archiving system for structured document management

05Intelligent content-based file renaming (YYYY-MM-DD - Topic.md)

06Automated extraction of key topics and action items from transcripts

ユースケース

01Automating the workflow of voice memo organization for productivity

02Generating searchable transcripts for interviews and academic lectures

03Converting meeting recordings into organized, speaker-labeled documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add warrenzhu050413/warren-claude-code-plugin-marketplace transcribe-assemblyai

For use in Claude.ai and ChatGPT

Download Skill

主な機能

01Advanced speaker diarization using Universal-3-Pro models

02Automatic detection of the latest local audio and video files

035 GitHub stars

04Categorized archiving system for structured document management

05Intelligent content-based file renaming (YYYY-MM-DD - Topic.md)

06Automated extraction of key topics and action items from transcripts

ユースケース

01Automating the workflow of voice memo organization for productivity

02Generating searchable transcripts for interviews and academic lectures

03Converting meeting recordings into organized, speaker-labeled documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add warrenzhu050413/warren-claude-code-plugin-marketplace transcribe-assemblyai

For use in Claude.ai and ChatGPT

Download Skill