Agent skill

Audio

by autonomous-ai in autonomous-ai/Physical-AI-Operating-System

Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio.

Apache-2.0Auto-check passedMedia & Creative

Install Audio

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System audio --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/audio .claude/skills/audio && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "audio" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio into .claude/skills/audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System audio --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/audio .agents/skills/audio && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "audio" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio into .agents/skills/audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System audio --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/audio .cursor/skills/audio && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "audio" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio into .cursor/skills/audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/autonomous-ai/Physical-AI-Operating-System.git --path skills/audio

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System audio --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/audio .gemini/skills/audio && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "audio" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio into .gemini/skills/audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System audio

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/audio .github/skills/audio && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "audio" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio into .github/skills/audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System audio --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/audio .opencode/skills/audio && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "audio" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/audio into .opencode/skills/audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: audio
GitHub stars: 381
Token cost: ~1k tokens
SKILL.md length: 458 words
Files: 2
Skills in repo: 28
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio.

Works in 4 steps: Determine the user's audio hardware need → For explicit volume/tone/recording… → Execute the appropriate API call → …
TTS/speech (that is the Voice skill)
SKILL.md covers Quick Start, Workflow, Examples and Tools, plus 3 more sections
Calls curl

What it does

Audio is an agent skill from autonomous-ai/Physical-AI-Operating-System. Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio. Do NOT use for TTS/speech (that is the Voice skill).

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.json`).

It sits in Media & Creative, covering Text to speech and voice. The repository describes itself as: The open-source operating system for physical AI. The licence is Apache-2.0.

When your agent uses it

TTS/speech (that is the Voice skill)
Tasks that involve Text to speech and voice

Example prompts

“/audio”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Determine the user's audio hardware need
For explicit volume/tone/recording requests, call the requested endpoint directly and handle its response. Use GET /audio for device…
Execute the appropriate API call
Confirm the action to the user

What it can do on your machine

Read from SKILL.md and the folder at commit f1b9ebe. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audio loads about 1k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 458 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~40
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from autonomous-ai/Physical-AI-Operating-System at commit f1b9ebe, republished under its Apache-2.0 licence (© autonomous-ai). 458 words, ~1,010 tokens.

Download SKILL.mdSave it as .claude/skills/audio/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: audio
description: Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio. Do NOT use for TTS/speech (that is the Voice skill).

Audio Control

Quick Start

Control the device's speaker and microphone hardware directly. Use this for volume adjustments, test tones, and raw audio recording. This is LOW-LEVEL hardware control only.

Workflow

Determine the user's audio hardware need:
- Volume adjustment -> use POST /audio/volume
- Check current volume -> use GET /audio/volume
- Diagnostics / test -> use POST /audio/play-tone
- Raw recording -> use POST /audio/record
For explicit volume/tone/recording requests, call the requested endpoint directly and handle its response. Use GET /audio for device diagnostics, not routine preflight. Relative volume changes still need GET /audio/volume.
Execute the appropriate API call
Confirm the action to the user

Examples

Input: "Louder please" / "Turn it up" Output: Check current volume with GET /audio/volume, then increase by ~15 with POST /audio/volume. Confirm: "Volume set to 85%."

Input: "Set volume to 50%" Output: Call POST /audio/volume with {"volume": 50}. Confirm: "Volume set to 50%."

Input: "Mute" / "Too loud" Output: Call POST /audio/volume with {"volume": 0}. Confirm: "Muted."

Input: "I can't hear you" Output: Check current volume with GET /audio/volume, then increase it. Confirm with the new level.

Input: "Say something" / "Tell me a joke" Output: Do NOT use this skill. Just reply normally — your voice pipeline handles TTS automatically.

Tools

Use Bash with curl to call the HTTP API at http://127.0.0.1:5001.

Check audio devices

bash

curl -s http://127.0.0.1:5001/audio

Response:

json

{
  "output_device": 0,
  "input_device": 1,
  "available": true
}

Set volume

bash

curl -s -X POST http://127.0.0.1:5001/audio/volume \
  -H "Content-Type: application/json" \
  -d '{"volume": 70}'

Volume range: 0 (mute) to 100 (max).

Get current volume

bash

curl -s http://127.0.0.1:5001/audio/volume

Response: {"control": "Speaker", "volume": 70}

Play test tone

bash

curl -s -X POST "http://127.0.0.1:5001/audio/play-tone?frequency=440&duration_ms=500"

Plays a sine wave. Use for audio testing only. Keep it short (< 1 second).

Show full SKILL.md (209 more words)Show less

Record audio

bash

record_dir=$(mktemp -d /tmp/autonomous-recording.XXXXXX) &&
curl --fail --silent --show-error -X POST \
  "http://127.0.0.1:5001/audio/record?duration_ms=3000" \
  --output "$record_dir/recording.wav" &&
printf 'Recording saved: %s\n' "$record_dir/recording.wav"

Records from the microphone and returns WAV bytes; save them to a unique file rather than printing binary data to the model. Adapt the duration to the user's request. Report the path only after the request succeeds; a failed request may leave an empty or partial file and is not a recording result. Do not re-record automatically after an uncertain outcome.

Error Handling

If GET /audio returns "available": false, inform the user: "The speaker/microphone is not connected right now."
If the API is unreachable, inform the user: "I couldn't access the audio hardware. The service may be unavailable."
If the user requests a volume outside 0-100, clamp to the valid range.

Rules

Default volume is usually 70%. Adjust based on user preference.
Audio = volume knob, raw mic recording, test beeps. No AI speech processing.
Voice = AI-powered speech (TTS/STT). Uses Audio hardware underneath but is a separate skill.
When the user says "I can't hear you" or "too loud", adjust volume via this skill.
Do NOT use this skill for TTS or speech output — that is handled by the Voice skill and the automatic voice pipeline.

Output Template

[Audio] {action} — {details}

Examples:

[Audio] Volume set — 70%
[Audio] Volume set — muted (0%)
[Audio] Test tone played — 440Hz, 500ms
[Audio] Recording captured — 3000ms

Files

SKILL.md and 1 other file in skills/audio of autonomous-ai/Physical-AI-Operating-System.

SKILL.md
skill.json

Open the folder on GitHubat commit f1b9ebe

Compare with similar skills

Audio next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audio compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Audio this skillautonomous-ai/Physical-AI-Operating-System	381	—	~1k	Automated safety check: Pass	Apache-2.0	today
MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo	129k	—	~2.1k	Automated safety check: Warn	MIT	today
HyperFrames Media Useheygen-com/hyperframes	59k	—	~2.4k	Automated safety check: Pass	Apache-2.0	today
Videodbaffaan-m/ECC	275k	3 repos	~3.5k	Automated safety check: Notes	MIT	3 days ago
Musictadaspetra/loop	296	3 repos	~827	Automated safety check: Pass	MIT	6 days ago
Openspec OnboardSAP/e-mobility-charging-stations-simulator	227	25 repos	~3.5k	Automated safety check: Pass	MIT	today

Similar skills

MoneyPrinterTurbo Video Generator
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
129k GitHub stars~2.1k tokensUpdated today
Media & CreativeAuto-check: warnings
HyperFrames Media Use
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
59k GitHub stars~2.4k tokensUpdated today
Media & CreativeAuto-check passed
Videodb
affaan-m/ECC
Ingest, index, search, edit, and monitor video and audio with the VideoDB Python SDK — upload from files, URLs, or RTSP feeds, build spoken and scene indexes with timestamped search and playable…
275k GitHub starsUsed in 3 repos~3.5k tokens
Media & CreativeAuto-check: notes
Music
tadaspetra/loop
Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.
296 GitHub starsUsed in 3 repos~827 tokens
Media & CreativeAuto-check passed
Openspec Onboard
SAP/e-mobility-charging-stations-simulator
Official
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
227 GitHub starsUsed in 25 repos~3.5k tokens
Media & CreativeAuto-check passed
Blog Audio
AgriciDaniel/claude-blog
Generate audio narration of blog posts using Google Gemini TTS.
2.3k GitHub starsUsed in 1 repo~2.2k tokens
Media & CreativeAuto-check: notes

Questions about Audio

What does Audio do?

Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio. Audio is an agent skill from autonomous-ai/Physical-AI-Operating-System. Low-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio.

When should I use Audio?

Audio fits situations like: TTS/speech (that is the Voice skill); tasks that involve Text to speech and voice.

How do I install Audio in Claude Code?

Run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a claude-code`. Or copy the skill folder (skills/audio in autonomous-ai/Physical-AI-Operating-System) into .claude/skills/audio in your project. Claude Code loads it when a task matches its description.

How do I install Audio in Codex?

Run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a codex`. Or copy the skill folder (skills/audio in autonomous-ai/Physical-AI-Operating-System) into .agents/skills/audio in your project. Codex loads it when a task matches its description.

Can I use Audio in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill audio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audio, .gemini/skills/audio, .github/skills/audio and .opencode/skills/audio in your project.

What does Audio need to run?

Going by SKILL.md and its folder, Audio needs the command-line tools its instructions call (curl).

Does Audio access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Audio safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audio use?

Audio is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audio use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audio?

Skills that share tags, products or a category with Audio: MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars), HyperFrames Media Use (heygen-com/hyperframes, 59k stars), Videodb (affaan-m/ECC, 275k stars) and Music (tadaspetra/loop, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audio?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/Physical-AI-Operating-System, which has 381 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

Source: autonomous-ai/Physical-AI-Operating-System on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Audio

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Audio Control

Quick Start

Workflow

Examples

Tools

Check audio devices

Set volume

Get current volume

Play test tone

Record audio

Error Handling

Rules

Output Template

Files

Compare with similar skills

Similar skills

More from autonomous-ai/Physical-AI-Operating-System

Related

Questions about Audio