What is voice-control?

A hands-free voice interface for coding agents that accepts spoken instructions and can read short progress updates aloud.

It is for voice conversations, dictating coding tasks, hearing brief updates, and asking spoken questions during work.

It lets users work by speaking when typing is inconvenient, while requiring the agent to confirm what it heard.

voice-control — Skill for Claude Code and Codex by zanezhao0708

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 zanezhao0708/voxagent --skill voice-control

Clone the repo

git clone --depth 1 https://github.com/zanezhao0708/voxagent

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/zanezhao0708/voxagent/voice-control/github.svg)](https://agentmods.dev/skills/zanezhao0708/voxagent/voice-control)

Your own site

<a href="https://agentmods.dev/skills/zanezhao0708/voxagent/voice-control"><img src="https://agentmods.dev/badge/skills/zanezhao0708/voxagent/voice-control/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/zanezhao0708/voxagent/voice-control"><img src="https://agentmods.dev/badge/skills/zanezhao0708/voxagent/voice-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 688 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	$0.00067	$0.00688
Opus 5.5	$0.00027	$0.00275
Sonnet 5.5	$0.00013	$0.00138
Haiku 4.5	$0.00007	$0.00069

Measured 1mo ago against content hash d4a382abc562, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

voice-control 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 1mo 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/voice-control/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice Control

You have voice tools from the voxagent MCP server. Use them to interact by voice — never guess what the user said, always call a tool.

When to use

The user says "voice mode / 语音模式 / listen up" → switch to voice: all further questions and confirmations go through ask_user, summaries via speak.
The user asks you to "read this aloud / 念一下" → speak a condensed version (max 2 sentences).
The user says "take dictation / 我说你们记" → call listen and treat the transcript as their message.

Rules

Spoken replies must be short. Max 2 sentences per speak call. Details stay in the chat; voice carries the headline.
Never invent audio input. If listen returns "[nothing heard]", say so and retry once, then fall back to text.
Language mirroring. Reply by voice in the language the user spoke. Transcripts may be mixed-language; follow the dominant one.
Announce long tasks. Before a step that takes >30s (builds, big refactors, test suites), speak a one-line heads-up like "Tests are running, about a minute."
Errors are spoken too. If something fails while in voice mode, speak a one-liner plus the fix you are attempting.
Degrade gracefully when voice fails. If speak errors or returns 0, do not retry in a loop — deliver the same message as text and note that audio is unavailable. Voice is an enhancement, never a blocker.

Push-to-talk context

The user may drive you with the global push-to-talk hotkey instead of typing. Transcripts then arrive as plain messages with no "voice mode" preamble. Treat a short, imperative spoken-style message (e.g. "run the tests") as a voice instruction and reply with a brief speak confirmation plus the normal text detail.

When voice fails

listen → "[nothing heard]": retry once, then continue in text.
speak errors: fall back to text; suggest voxagent doctor to the user.
Repeated STT/TTS failures: tell the user to run voxagent doctor and check mic permission / pip install 'voxagent[local]'.

Read the full file on GitHub · 62 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.

1mo ago First seen · 62 lines · 67 tokens per session scan A d4a382abc562

Subscribe to this mod's changes

voice-control is a skill published in the GitHub repository zanezhao0708/voxagent (10 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 688 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 2026-08-31.

Claude Code Productivity ai-agents mcp speech-recognition tts voice-agent

audiobook-maker

A workflow for turning long text, novels, and reports into spoken audio files. Text longer than 3,000 Chinese characters is split into smaller sections before speech is generated.

MerkyorLynn/Lynn · 36 tokens

obsidian-bases

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

bozhouDev/video-skills-toolkit · 63 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

voice-control