A connection to Groq, an AI service, that lets an agent receive spoken messages and turn audio files into written text.

Use it to enable microphone conversations, receive voice messages, and transcribe audio.

It removes the need to type messages and allows the agent to understand audio such as OGG, M4A, and MP3 files.

groq-audio — Skill for Claude Code by DGatoM/DG-Claw

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 DGatoM/DG-Claw --skill groq-audio

Clone the repo

git clone --depth 1 https://github.com/DGatoM/DG-Claw

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dgatom/dg-claw/groq-audio/github.svg)](https://agentmods.dev/skills/dgatom/dg-claw/groq-audio)

Your own site

<a href="https://agentmods.dev/skills/dgatom/dg-claw/groq-audio"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/groq-audio/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dgatom/dg-claw/groq-audio"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/groq-audio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,110 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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.01110
Opus 5.5	$0.00035	$0.00444
Sonnet 5.5	$0.00017	$0.00222
Haiku 4.5	$0.00009	$0.00111

Measured 13d ago against content hash 1bb88c2d7329, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

groq-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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/testar_chave.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/groq-audio/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Groq: falar por áudio com o agente

A Groq transcreve áudio de graça e muito rápido. Com a chave dela, o microfone do chat funciona e eu consigo entender os áudios que o dono manda (ogg, m4a, mp3).

Atenção: é Groq (a empresa de inferência, console.groq.com), não Grok da xAI. São empresas diferentes. A chave certa começa com gsk_.

Regras da conversa

Uma etapa por vez. Só passo para a próxima quando o dono confirmar a anterior.
Linguagem de dia a dia. Nada de "variável de ambiente", "container" ou "arquivo".
A chave nunca aparece em mensagem minha, em comando ou em log. O dono cola só no campo de senha do bloco dgcofre.

Passo 1: criar a chave (grátis)

Peça, uma etapa de cada vez:

Abrir https://console.groq.com/keys no navegador.
Entrar com a conta do Google ("Continue with Google").
Clicar em Create API Key, dar um nome qualquer (ex.: "meu agente") e confirmar.
Copiar a chave que aparece (começa com gsk_). Ela só aparece uma vez.

Se o dono disser que a chave começa com xai-, é a Grok: explique a diferença e volte ao item 1.

Passo 2: guardar a chave

A chave nunca é colada no chat. Responda com este bloco, que a tela da conversa transforma num campo de senha ligado direto ao cofre:

GROQ_API_KEY
Chave da Groq

Quando chegar "[cofre] GROQ_API_KEY guardada (final xxxx).", responda curto ("Tá salvo.") e siga. Se o dono colar a chave no chat por engano, avise que ela ficou exposta, peça para apagar essa chave na Groq e gerar outra, e mande o bloco de novo. (Sem a tela da conversa, o caminho é a aba Cofre do painel, opção Groq.)

Depois de salva, rode o teste (se a chave ainda não estiver no ambiente, ela entra na próxima reinicialização do agente):

python3 ~/.claude/skills/groq-audio/scripts/testar_chave.py

Se der erro, o script diz em português o que fazer; repasse ao dono com suas palavras.

Passo 3: ligar o microfone do chat

O microfone do chat é transcrito pelo DG Claw Web, que lê a chave de outro lugar (o web.env da plataforma). Eu não tenho acesso a ele. Peça ao dono:

Read the full file on GitHub · 93 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/testar_chave.py 3.3 KB runs code

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.

13d ago Changed 1bb88c2d7329
19d ago First seen · 93 lines · 87 tokens per session scan A cb3d2e992030

Subscribe to this mod's changes

groq-audio is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,110 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-18.

Productivity

groq-audio next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
groq-audioDGatoM/DG-Claw	Skill	20	2d ago	MIT	A	87	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex