# Add Voice

Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice...

- Repository: https://github.com/cursor/plugins (15000 stars)
- Category: Testing
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add cursor/plugins --skill add-voice -g -a claude-code -y`
Codex: `npx skills add cursor/plugins --skill add-voice -g -a codex -y`
Cursor: `npx skills add cursor/plugins --skill add-voice -g -a cursor -y`
Gemini CLI: `npx skills add cursor/plugins --skill add-voice -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add cursor/plugins`

## Description

Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice to an app, including replacing an STT-LLM-TTS cascade or OpenAI Realtime.   Wire speech-to-speech, safe auth, and app mic. Composer: waveform button, mic icon reserved for dictation. For mic-to-text only use /add-dictation; to speak text replies use /add-read-aloud. To add debug logging and fix from logs use /debug-voice.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Add Voice

Add Grok Speech to Speech to an existing app. Run on `/add-voice`, typed **Voice Mode**, or clear “add Grok voice” intent.

## Goal

Working duplex path: user-app mic in, audio out, `wss://api.x.ai/v1/realtime?model=grok-voice-latest`, safe auth. Cursor has no native mic; wire the **app** (or a sample client), not the IDE.

## Protocol first

Language-agnostic event loop. **TypeScript samples default.** Short Python twins only where the client API differs (e.g. `ws` vs `websockets`).

## Docs

- https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech
- https://docs.x.ai/developers/model-capabilities/audio/ephemeral-tokens
- Pricing (cite docs only): https://docs.x.ai/developers/pricing (~$0.08/min STS + $0.004/text item; max session 120 min)

## Steps

1. **Map the app**
   - Stack: none, OpenAI Realtime, STT→LLM→TTS cascade, TTS/STT only.
   - Client: web / Node / iOS / Android / server.
   - If a cascade or OpenAI Realtime exists: replace it with the single duplex loop below (URL, model, voice, event diffs); keep standalone `/v1/stt` or `/v1/tts` only if the product still needs one-shot listen or speak outside the agent.

2. **Auth**
   - Server: Bearer `XAI_API_KEY`.
   - Browser/mobile: backend `POST https://api.x.ai/v1/realtime/client_secrets`, client uses ephemeral token (Bearer or browser `sec-websocket-protocol`: `xai-client-secret.<token>`).
   - Never put a long-lived key in client bundles. Do not paste keys in chat.

The rest: https://github.com/cursor/plugins/blob/HEAD/grok-voice/skills/add-voice/SKILL.md