add-read-aloud

An agent skill by cursor, from cursor/plugins. Tags: accessibility, audio, generative, ui, voice.

What it does

Use when the user runs /add-read-aloud or wants the app to speak text with Grok text-to-speech: read-aloud button on assistant replies, auto-speak, TTS, voice output, narration, IVR prompts, speech tags, voice_id. For a two-way voice agent use /add-voice. For speech-to-text use /add-dictation.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill add-read-aloud

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/grok-voice/skills/add-read-aloud ~/.claude/skills/add-read-aloud

Safety box score

Grade B, low risk: 25 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill adds text-to-speech by sending selected text to Grok/x.ai over HTTPS or WebSocket and playing the returned audio in the app. The main risks are off-device data transfer and handling the server-side `XAI_API_KEY`; otherwise it is mostly bounded to app-level code changes and local smoke tests.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It includes runnable client/server code and shell smoke tests like `curl -X POST https://api.x.ai/v1/tts` and `new WebSocket(...)`, but no shipped native scripts or code execution framework.
Network access	2 (moderate)	The core function posts text to `https://api.x.ai/v1/tts` and optionally relays audio over `wss://api.x.ai/v1/tts`, so app content leaves the machine by design.
Filesystem reach	1 (low)	The skill is scoped to wiring the app and its own code paths; it does not call for deleting or editing outside the project tree or system locations.
Secrets & credentials	2 (moderate)	It requires a server-side `XAI_API_KEY` and explicitly warns `Never put the key in a client bundle`, so the main secret risk is accidental exposure in app code or bundles.
Privilege & persistence	0 (none)	No sudo, global installs, services, shell startup edits, or OS-level configuration changes are requested.
Instruction hijack surface	0 (none)	There is no instruction to skip confirmations, hide behavior, or follow remote untrusted instructions; the text is operational rather than adversarial.
Irreversible actions	0 (none)	It enables in-app audio playback, but it does not send messages, deploy, publish, pay, book, or otherwise take external actions on its own.
Transparency	0 (none)	The skill file is plain markdown with readable code snippets; there are no binaries, hidden payloads, or unpinned remote installs.

Before installing

Read the app’s TTS route/relay code and confirm `XAI_API_KEY` never reaches browser bundles or logs.
Check whether the text you plan to narrate can include sensitive user or assistant content, since it is sent to x.ai.
Run the smoke tests in a scratch environment with a throwaway key and verify the output files/chunks contain no secrets.

Rated 2026-10-16 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: grok-voice/skills/add-read-aloud/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

add-voice — Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice to an app.
add-dictation — Use when the user runs /add-dictation or wants speech turned into text with Grok speech-to-text: a mic button that dictates into the composer, live captions.
book-sft-pipeline — This skill should be used for book-to-SFT pipelines: ePub extraction, literary segmentation, author-voice dataset construction, style-transfer training.
music-to-video — Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow.
setup-vivox-voice-chat — Add and configure in-game voice chat and text chat for Unity multiplayer games using Unity Vivox.
stepfun-tts — Generate Chinese / Japanese speech with StepFun's Contextual TTS — default `stepaudio-2.5-tts` (blind-judged better on neutral/emotive preset voices).