add-read-aloud — Claude Code skill for text-to-speech
Builds Grok text-to-speech into an existing app, for read-aloud controls, automatic playback, or spoken page content.
npx skills add cursor/plugins --skill add-read-aloud -a claude-codeWhat add-read-aloud does
The skill guides an agent through adding speech playback for completed assistant replies, narration, or generated audio files. Its default route sends text to Grok TTS from the server and returns an MP3. Keep XAI_API_KEY server-side; it must not end up in the browser bundle.
The instructions cover turning formatted text into speech-ready input, handling long messages, and reflecting loading and playback in the app’s controls. Requests are limited to 15,000 characters, so longer text needs splitting or the streaming route. Browser streaming requires a backend relay. Auto-speak should be opt-in and start only after a user gesture.
What it helps with
- add a speaker control to completed assistant replies
- narrate page text or create an audio file
- split long input into TTS-sized parts
- keep the Grok API key out of client code
Example prompts for the agent
- Add a control that reads completed assistant replies aloud with Grok TTS.
- Set up page narration and split long text before sending it for speech.
- Make automatic reply playback optional and start it after a user gesture.
How to install add-read-aloud
1Skills CLI (Vercel)
npx skills add cursor/plugins --skill add-read-aloud -a claude-code2Manually: put the files in place
~/.claude/skills/add-read-aloud/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/add-read-aloud/
1Skills CLI (Vercel)
npx skills add cursor/plugins --skill add-read-aloud -a codex2Manually: put the files in place
.agents/skills/add-read-aloud/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add cursor/plugins --skill add-read-aloud -a cursor2Manually: put the files in place
.cursor/skills/add-read-aloud/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install cursor/plugins add-read-aloud2Manually: put the files in place
.github/skills/add-read-aloud/SKILL.md1Skills CLI (Vercel)
npx skills add cursor/plugins --skill add-read-aloud -a gemini-cli2Platform CLI
gemini skills install https://github.com/cursor/plugins --path grok-voice/skills/add-read-aloudManually: put the files in place
.devin/skills/add-read-aloud/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add cursor/plugins --skill add-read-aloud -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about add-read-aloud
How do I install add-read-aloud in Claude Code?
Run npx skills add cursor/plugins --skill add-read-aloud -a claude-code. The skill file is at ~/.claude/skills/add-read-aloud/SKILL.md.
What does add-read-aloud do?
It guides an agent in adding Grok TTS playback to an existing app, such as speech controls for assistant replies or narration for other text. The default approach returns audio as an MP3.
What does add-read-aloud need to run?
The server needs XAI_API_KEY; keep it out of browser code. Browser-based streaming also needs a backend relay.