# Paxa Labs

This MCP server gives an agent speech, transcription, translation, OCR, and document-field extraction tools for local work.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 10
- Author: paxalabs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/paxalabs/mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/paxa-labs

## What it does

Paxa Labs connects an agent to voice tools for spoken output and input. It can play short replies, process longer text through an audio queue, write speech to MP3, Opus, or WAV, and produce matching subtitles. Recording transcription supports speaker labels, word timings, and pause data for cutting.

The server also translates text into Thai, reads local PDFs and images with OCR, and fills typed fields from document scans. OCR accepts PDF, PNG, JPEG, and WebP files. A Paxa API key must be supplied as `PAXA_API_KEY`; without it, the server cannot connect. API calls consume credits, and the tool set is currently beta.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `PAXA_API_KEY`, `PAXA_OUTPUT_DIR`, `PAXA_DEFAULT_VOICE` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env PAXA_API_KEY=<PAXA_API_KEY> --env PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> --env PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> --transport stdio paxa-labs -- npx -y @paxalabs/mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add paxa-labs --env PAXA_API_KEY=<PAXA_API_KEY> --env PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> --env PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> -- npx -y @paxalabs/mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "paxa-labs": {
            "command": "npx",
            "args": [
                "-y",
                "@paxalabs/mcp"
            ],
            "env": {
                "PAXA_API_KEY": "<PAXA_API_KEY>",
                "PAXA_OUTPUT_DIR": "<PAXA_OUTPUT_DIR>",
                "PAXA_DEFAULT_VOICE": "<PAXA_DEFAULT_VOICE>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "paxa-labs": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@paxalabs/mcp"
            ],
            "env": {
                "PAXA_API_KEY": "<PAXA_API_KEY>",
                "PAXA_OUTPUT_DIR": "<PAXA_OUTPUT_DIR>",
                "PAXA_DEFAULT_VOICE": "<PAXA_DEFAULT_VOICE>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e PAXA_API_KEY=<PAXA_API_KEY> -e PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> -e PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> paxa-labs npx -y @paxalabs/mcp
```
Replace <…> with your own values

## When to use it
- play an agent response through local speakers
- save generated speech as an audio file
- transcribe a recording with subtitles
- read a PDF or image with OCR
- fill typed fields from a scanned document

## Example prompts
- Read the change summary aloud with `speak`.
- Transcribe `meeting.mp4` with speaker labels and subtitles.
- Extract dates, amounts, and bank details from `invoice.pdf`.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
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