transcribe

transcribe is a skill for Claude Code from alejandro-ventures/llm-agnostic-icm-framework. It costs 46 tokens per session (1,114 once invoked), scanned A, original, Apache-2.0.

A local workflow that turns MP3 recordings into transcripts with speaker labels and timestamps using speech recognition and speaker separation.

In plain words
What is it for?
Use it to process MP3 files, identify different speakers, create Markdown and JSON transcripts, skip already processed files, and run the recognition and speaker-separation stages separately.
Why use it?
It keeps audio processing and transcript generation on the machine after the required model setup, so recordings do not need to be sent to an external service.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to process MP3 files, identify different speakers, create Markdown and JSON transcripts, skip already processed files, and run the recognition and speaker-separation stages separately.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe
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.

Any agent
npx skills add alejandro-ventures/llm-agnostic-icm-framework --skill transcribe
Clone the repo
git clone --depth 1 https://github.com/alejandro-ventures/llm-agnostic-icm-framework

Made for: Claude Code.

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.

agentmods badge for transcribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe/github.svg)](https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe)
Your own site
<a href="https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for transcribe

Your own site · 80×15
<a href="https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01114
Opus 5 $0.00023 $0.00557
Sonnet 5 $0.00009 $0.00223
Haiku 4.5 $0.00005 $0.00111

Measured 10d ago against content hash 3c6686fed2f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

transcribe 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 10d 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.

workflows/transcribe/.github/transcribe/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

transcribe

Sensitive audio: all inference is local — audio and transcripts never leave this machine. pyannote's models are license-gated on Hugging Face: ONE authenticated download at setup (see docs/README.md), after which every run executes with HF_HUB_OFFLINE=1 — network access is impossible, not merely avoided. The HF token can be revoked after setup.

Environment — two venvs, a deliberate exception to CONVENTIONS rule 10

Stage Engine Interpreter
ASR faster-whisper large-v3 (CUDA fp16 / CPU int8) workflows/transcribe/.venv-asr
Diarization pyannote/speaker-diarization-3.1 (pyannote.audio 4.x resolves it to the current community stack) workflows/transcribe/.venv-pyannote
Stages run as separate subprocesses — the two engines' CUDA/cuDNN DLLs segfault when
loaded into one process on Windows. Never merge them. requirements.txt pins both stacks.

Inputs

Source Location Why
mp3 files input/ recordings (copy reference audio here first — originals untouched)

Process

  1. Preflight (cheap, before ASR): ffprobe each mp3; skip cached/existing outputs. Truncation gate — compare each mp3's duration to a same-date video in --source-dir; if the mp3 is < 95% of the source it's flagged truncated and skipped (re-convert, or --allow-truncated). Channel-imbalance check warns if L/R RMS differ ≥ 6 dB. VRAM gate: if < 10 GB free, the message names the resident Ollama model; free it with --free-gpu (opt-in — it never seizes the GPU from another session by default) or --device cpu. 2. ffmpeg → 16 kHz mono WAV (temp). 3. ASR subprocess: word-level timestamps, language auto-detect per file. 4. Diar subprocess: pyannote whole-file (global clustering keeps speaker identity consistent; VRAM stays bounded ~8 GB even on 75-min calls — do NOT swap in a diarizer that loads the whole file into attention; that crashed this machine twice, hypervisor bugcheck). 5. Merge: per-WORD speaker attribution by diar overlap, then group into turns. 6. Write .md + .json via sandbox.guard_write. 7. Gate: overwrite needs explicit "yes" (--overwrite). 8. Append run-log + token-tracker entry.

Read the full file on GitHub · 63 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.

  1. 10d ago First seen · 63 lines · 46 tokens per session scan A 3c6686fed2f8

Subscribe to this mod's changes

transcribe is a skill published in the GitHub repository alejandro-ventures/llm-agnostic-icm-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,114 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

manim-video

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations…

agnt-gg/agnt · 0 tokens

astrophotography-processing

Router for astrophotography processing, troubleshooting, and safe workflow guidance across deep-sky, narrowband, planetary/lunar/solar, Milky Way landscape, comet, and mosaic data.

mickpletcher/AI-Skills · 44 tokens

arxiv

Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.

marysatasselshaped667/skills-collection-1 · 61 tokens

album-art-director

Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.

marysatasselshaped667/skills-collection-1 · 35 tokens

algorithmic-art

Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).

marysatasselshaped667/skills-collection-1 · 43 tokens

ablation-planner

Use when main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.

marysatasselshaped667/skills-collection-1 · 48 tokens