Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

xai-tts

Estrelas5

Forks0

Atualizado26 de junho de 2026 às 09:23

Use when the user asks to generate speech, text-to-speech, audio narration, voice output, or TTS with xAI/Grok through a Grok-connected xAI TTS tool.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

islee23520

islee23520/lfg

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

Mais deste repositório

mesmo repositório

start-work

islee23520/lfg

Execute a Prometheus work plan in GrokBuild with `/goal` state, Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and explicit continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.

2026-07-165

ulw-loop

islee23520/lfg

Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.

2026-07-165

ulw-plan

islee23520/lfg

MUST USE for planning before coding: 5+ steps, ambiguous scope, multiple modules, architecture decisions, a vague 'just make it good / figure out what to build' brief, or any request to plan, interview, or break work down. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode, just make it good, figure out what to build.

Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.

2026-07-165

eval

islee23520/lfg

Persistent code-mode kernels (JS/Python) for incremental computation — omp/senpi eval analog on GrokBuild via lfg MCP. Use when multi-step code execution, data exploration, or stateful REPL beats one-shot bash.

2026-07-155

name	xai_tts
description	Use when the user asks to generate speech, text-to-speech, audio narration, voice output, or TTS with xAI/Grok through a Grok-connected xAI TTS tool.

xAI TTS

Use this skill to generate speech audio through the Grok-connected xAI TTS tool.

Preferred Grok Tool Flow

Use search_tool to discover the available tool schema first:

{
  "query": "xai tts"
}

Call the returned xAI TTS MCP tool with the schema it reports. A typical payload is:

{
  "input": "Hello from Grok.",
  "voice_id": "eve",
  "language": "auto",
  "codec": "mp3"
}

Options

input: required text to speak.
voice_id: optional voice, commonly eve when supported.
language: optional language, commonly auto when supported.
codec: optional output codec.

Return the content type and explain where the audio artifact or base64 payload appears in the tool output.

Credential Safety

Use existing Grok/xAI credentials exposed by the host or MCP server. Never print, quote, summarize, or store OAuth tokens, refresh tokens, bearer tokens, or API keys.