domain-audio-speech

domain-audio-speech is a skill for Claude Code from mxslr/mlcraft. It costs 105 tokens per session (512 once invoked), scanned A, original, MIT.

A guide for machine-learning tasks involving recorded sound or speech. It covers turning speech into text, identifying sounds or speakers, finding keywords, and detecting events in audio.

In plain words
What is it for?
Use it for transcription, sound classification, keyword spotting, speaker identification or verification, sound-event detection, and audio or music analysis.
Why use it?
It helps select suitable audio representations, models, data splits, and measurements for different sound problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mlcraft plugin — 23 skills, 1 command, 1 agent shipped together

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/mxslr/mlcraft/domain-audio-speech
Any agent
npx skills add mxslr/mlcraft --skill domain-audio-speech
Clone the repo
git clone --depth 1 https://github.com/mxslr/mlcraft

Made for: Claude Code.

Or install mlcraft, the plugin that ships this one along with the rest of its 23 skills, 1 command, 1 agent.

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 domain-audio-speech

README.md
[![agentmods](https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-audio-speech.svg)](https://agentmods.dev/skills/mxslr/mlcraft/domain-audio-speech)
Your own site
<a href="https://agentmods.dev/skills/mxslr/mlcraft/domain-audio-speech"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-audio-speech.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 512 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.00512
Opus 5 $0.00053 $0.00256
Sonnet 5 $0.00021 $0.00102
Haiku 4.5 $0.00011 $0.00051

Measured 6d ago against content hash 384086c2af5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

domain-audio-speech 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 6d 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.

skills/domain-audio-speech/SKILL.md · 25 lines

What it actually says

Audio and Speech - Method Selection

Represent audio as a log-mel spectrogram for most classifiers, or feed the raw waveform to self-supervised speech models. Resample to the model's rate (16 kHz is common).

Decision table

Sub-task Recommended Notes
Speech recognition (ASR) Whisper (large-v3, or turbo for speed); wav2vec2 or HuBERT with CTC Whisper is strong and multilingual zero-shot. Metric is WER, never accuracy.
Audio or sound classification and tagging AST or PaSST (spectrogram transformers, AudioSet-pretrained); PANNs (CNN) log-mel input. Multi-label tagging uses mAP; single-label uses accuracy or macro F1.
Keyword spotting small CNN or MatchboxNet on log-mel on-device. Track accuracy and false-alarm rate.
Speaker verification or ID ECAPA-TDNN or x-vector embeddings + cosine similarity metric-learning. Metrics are EER and minDCF. Split by speaker.
Sound event detection CRNN or PaSST with framewise output event-based F1, PSDS.

Cross-cutting practice

  • Augment with SpecAugment, time and pitch shift, and noise or room-impulse mixing. Normalize levels.
  • Leakage: split by speaker, recording, or session, not by clip. The same speaker in train and test inflates results.
  • Metrics: WER (and CER) for ASR; mAP for multi-label tagging; EER for verification. Do not report plain accuracy for ASR.
  • Explainability: saliency or Grad-CAM on the spectrogram for classifiers; attention or confidence and alignment for ASR.
  • Improve accuracy: use accuracy-improvement-loop. Evaluate with rigorous-evaluation using the metric that fits the sub-task.
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. 6d ago First seen · 25 lines · 105 tokens per session scan A 384086c2af5c

Subscribe to this mod's changes

domain-audio-speech is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 512 once invoked, about $0.0005 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

transformers

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…

synthetic-sciences/openscience · 63 tokens

chief-data-officer

Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…

cbrock84/headcount · 88 tokens

ai-workflow-architect

Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…

cbrock84/headcount · 89 tokens

ai-ml-governance

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…

cbrock84/headcount · 83 tokens

data-engineering

Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone…

cbrock84/headcount · 67 tokens

llm-integration

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

yonatangross/orchestkit · 58 tokens