Skill

transcribe-assemblyai

Transcribe audio via AssemblyAI with word-level timestamps and speaker diarization. Best for meetings, interviews, and anything needing speaker labels or timecodes. Use when the user asks for a timestamped transcript, diarized transcript, or multi-speaker transcription.

npx claudepluginhub danielrosehill/claude-code-plugins --plugin claude-transcription

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Produce a transcript with word-level timestamps and speaker turns.

SKILL.md

Similar Skills

cache-components

139.3k

Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

Stats

Stars0

Forks0

Last CommitApr 19, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Transcribe (AssemblyAI, timestamped + diarized)

Produce a transcript with word-level timestamps and speaker turns.

Requirements

ASSEMBLYAI_API_KEY env var (name configurable in config.json).

Source audio accessible — AssemblyAI accepts URL or uploaded file.

How

Upload file: POST https://api.assemblyai.com/v2/upload (bytes of audio, Authorization: <key>).

Create transcript: POST https://api.assemblyai.com/v2/transcript with

{
  "audio_url": "<upload_url>",
  "speaker_labels": true,
  "punctuate": true,
  "format_text": true
}

Poll GET /v2/transcript/<id> until status == "completed".

Render output.

Speaker name mapping

If <source_stem>_speakers.json exists (from extract-speaker-samples), remap AssemblyAI's A/B/C labels to user-provided names.

Output convention

Save to <source_stem>.timestamped.md. Format:

[00:00:03] **Alice:** Welcome to the call. [00:00:07] **Bob:** Thanks for having me.

Also save raw AssemblyAI JSON to <source_stem>.assemblyai.json for downstream use.

Cost

Roughly $0.37/hr with speaker labels. Flag this if the audio is very long (>4 hours).