What is import-audio?

A workflow for importing audio from a Mac desktop or Voice Memos and converting it into written transcripts. Transcription means turning spoken words in an audio recording into text.

Finding supported audio files, moving or copying them into the import area as required, transcribing them with Whisper, and storing the resulting transcripts.

It organizes audio files and applies the project’s required storage and transcription process instead of handling each recording manually.

import-audio — Skill for Claude Code and Codex by markmhendrickson: A workflow for importing audio from a Mac desktop…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/markmhendrickson/ateles/import-audio

Any agent

npx skills add markmhendrickson/ateles --skill import-audio

Clone the repo

git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/import-audio.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/import-audio)

Your own site

<a href="https://agentmods.dev/skills/markmhendrickson/ateles/import-audio"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/import-audio.svg" alt="Measured on agentmods" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,265 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00053	$0.01265
Opus 5	$0.00026	$0.00633
Sonnet 5	$0.00011	$0.00253
Haiku 4.5	$0.00005	$0.00127

Measured 4d ago against content hash ba6078dbb38c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

import-audio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/import-audio/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Import Audio

Import audio files from Desktop and macOS Voice Memos, transcribe with Whisper, and store transcriptions. Follows data entry and migration rules for locations and storage order.

When to Use

Use this skill when:

User says "import audio", "import audio files", "transcribe audio from desktop", or "import voice memos"
User wants to batch-import and transcribe audio from Desktop or Voice Memos

Required Documents (load first)

Audio import workflow: docs/data_entry_requirements_rules.mdc (Audio File Import Workflow)
Storage order: docs/neotoma_parquet_migration_rules.mdc (Neotoma first, then Parquet if still used)

Workflow

Scan sources for audio files (.wav, .mp3, .m4a, .ogg, .flac, .aac, .wma, .mp4, .webm, .qta):
- ~/Desktop
- ~/Library/Group Containers/group.com.apple.VoiceMemos.shared/Recordings/ (macOS Voice Memos)
Import files to $DATA_DIR/imports/audio/ with timestamped names:
- Desktop files are moved.
- Voice Memos files are copied (system-managed; do not move).
Transcribe using OpenAI Whisper via execution/scripts/transcribe_audio.py, or run the full pipeline with execution/scripts/import_audio_from_desktop.py.
Store transcriptions: Neotoma MCP first per migration rules; if transcriptions still in Parquet, use $DATA_DIR/transcriptions/transcriptions.parquet via Parquet MCP.
Auto-invoke /analyze-meeting on each successfully transcribed file. The analyze-meeting skill's own "skip silently" rule (≥2 speakers OR ≥200 words AND a commitment verb) handles non-meeting audio (voice memos, lectures, ambient recordings) so unrelated audio does not produce spurious tasks/emails/issues. Disable per-run with --no-analyze.
Link continuations: After all transcriptions are stored, review the batch for recordings that are continuations of each other (same topic, recorded within minutes, or explicitly referencing a previous memo). Create a continues relationship between them in Neotoma (earlier → later).
Extract and relate entities: For each transcription, identify mentioned entities — people, places, organizations, topics, tasks, decisions, feedback items, etc. — and create or update corresponding Neotoma entities. Then relate each transcription to every entity it produced or updated using a mentions relationship (transcription → entity).

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 74 lines · 53 tokens per session scan A ba6078dbb38c

Subscribe to this mod's changes

import-audio is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,265 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Autonomous Agents Creative and media LLM aauth agent-swarm ai-agents claude

implement

Автономная реализация задачи через изолированный субагент с чистым контекстом.

cryndoc/polisade-orchestrator · 4 tokens

qqbot-media

QQ Bot 媒体发送指南。教 AI 如何发送图片给用户。.

nanoAgentTeam/research-claw · 21 tokens

imagine

How to use the imagegen and imageedit tool calls in Grok Build: when to build a visual with code instead of generating it, prompt-craft, reference-first handling of real people, factual grounding, and asset-consistency. Load this whenever generating or editing an image is on the table, i.e. when an imagegen or…

RoyZhao1991/LingShu · 97 tokens

import-audio