# narrador

Turn PDFs, Word files, EPUBs, text, and X posts into audio with word-level timing data. Use it when an agent needs to narrate a document or post.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: narrador-io
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/narrador-io/narrador-mcp
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/narrador

## What it does

narrador connects an agent to narrador files and narrador X. For a document, the agent can submit text or an uploaded file ID, start a job, check its progress, and retrieve audio with timings for each word. For an X post, it can request audio using the post ID or URL.

The MCP server runs remotely, so there is no local server installation. Connect through OAuth or an API key; audio jobs use narrador credits. By default, the service detects a document’s language when choosing a voice. If it has no voice for that language, the job fails, so provide `voiceId` and `accent` yourself in that case.

## Requirements
- Remote server: `https://api.narrador.io/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http narrador https://api.narrador.io/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add narrador --url https://api.narrador.io/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "narrador": {
            "url": "https://api.narrador.io/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "narrador": {
            "type": "http",
            "url": "https://api.narrador.io/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http narrador https://api.narrador.io/mcp
```

## When to use it
- turn a PDF into narrated audio with word timings
- convert document text into audio
- generate audio from an X post
- check the progress of an audio job

## Example prompts
- Narrate this document and return the audio with word timings.
- Generate audio for this X post: [post URL].
- Check the narrador job and retrieve its completed result.

## Similar
- [Reactive Resume](https://affpapa.org/en/nevibecode/mcp/reactive-resume.md) — MCP server · ★ 44908
- [Sui Knowledge Base (kapa.ai)](https://affpapa.org/en/nevibecode/mcp/sui-knowledge-base-kapaai.md) — MCP server · ★ 7785
- [Claude Code Ultimate Guide](https://affpapa.org/en/nevibecode/mcp/claude-code-ultimate-guide.md) — MCP server · ★ 6258
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5585
- [RevoGrid DataGrid MCP Pro](https://affpapa.org/en/nevibecode/mcp/revogrid-datagrid-mcp-pro.md) — MCP server · ★ 3451
- [Claude Code Explorer MCP](https://affpapa.org/en/nevibecode/mcp/codeaashu-claude-code-explorer-mcp.md) — MCP server · ★ 3412

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md