@paxalabs/mcp

Official MCP server for the Paxa Labs API: Thai, English, and Mandarin Chinese speech AI for your agent, including local audio playback.

An agent connected to this server can speak out loud through your machine's speakers, read long content aloud as a managed playback queue, save speech to audio files, listen for a spoken reply, transcribe recordings with subtitles, translate any language into Thai, read PDFs and images with OCR, and extract typed fields from documents.

Beta. The tool set is complete and tested end to end, but tool names and behavior may still change before 1.0 as feedback comes in. Report problems at https://github.com/paxalabs/mcp/issues.

Quick start

You need a Paxa API key from paxalabs.com. New accounts include free credits.

Claude Code

claude mcp add paxa -e PAXA_API_KEY=pxa_your_key_here -- npx -y @paxalabs/mcp

Claude Desktop, Cursor, and other MCP clients

Add to your client's MCP configuration (for Claude Desktop: claude_desktop_config.json):

{
  "mcpServers": {
    "paxa": {
      "command": "npx",
      "args": ["-y", "@paxalabs/mcp"],
      "env": {
        "PAXA_API_KEY": "pxa_your_key_here"
      }
    }
  }
}

One click for Cursor or VS Code: the buttons install the same entry into ~/.cursor/mcp.json or VS Code's MCP settings. Then replace pxa_your_key_here in the paxa entry with your key.

Tools

Tool	What it does	Credits
speak	Synthesize a short line and play it through the speakers, blocking until done	10 per 1000 chars
queue_speech	Read long content aloud: auto-chunks, synthesizes ahead while playing, returns immediately	10 per 1000 chars
control_playback	Control the shared audio queue: status, pause, resume, skip, clear	free
play_audio	Play a local audio file through the speakers	free
text_to_speech	Synthesize speech to an audio file (mp3, opus, wav) without playing it: long scripts are split and joined into one file, and subtitles writes a matching srt or vtt	10 per 1000 chars (12.5 with subtitles)
translate_to_thai	Translate any language into Thai, with formality, glossary, and context controls	25 per 1000 chars
ocr_document	OCR a local PDF, PNG, JPEG, or WebP into Markdown or structured blocks	6.5 per page
extract_fields	Fill a schema of typed fields (Thai IDs, dates, amounts, banks, line items) from a local PDF or image; every value is printed in the document or null with the reason	13 per page (19.5 for schemas over 50 fields)
listen	Record one spoken turn from the microphone and return its transcript; the API detects when the user stops talking	12.5 per minute listened
send_feedback	Rate an output or report a problem to the Paxa team, tied to the request ids the tools print	free
transcribe_audio	Transcribe a local recording or video (Thai, English, mixed) to text, with optional speaker labels, word timings, srt or vtt subtitles, and a list of pauses to cut	8.33 per minute
list_voices	The TTS voice roster with character notes	free
list_models	Available models, limits, and pricing	free
get_account	Credit balance, plan, and rate limits	free

All audio flows through one ordered queue, so sounds never overlap: speak lines slip in ahead of queued long-form segments, and queue_speech keeps a book or article flowing gap-free by synthesizing the next segment while the current one plays.

With a streaming-capable player installed (see below), speech starts on the first bytes from the API instead of after the full download: about 0.3 s to the first word regardless of length, versus 0.7 s for a short line and 2.5 s for a long paragraph when buffered.

Voice mode for Claude Code

Three pieces turn Claude Code into something you can walk away from: it talks when it has news, and it calls you when it needs you.

1. Install the server (Quick start above).

2. Tell Claude when to talk. Add this to ~/.claude/CLAUDE.md, or to one project's CLAUDE.md:

## Voice

I have the Paxa MCP server (tools: speak, queue_speech, control_playback).
I am often away from the screen, so use voice like this:

- At the end of a turn where you did real work, call speak with a one or
  two sentence summary before writing the final message: what you did,
  what is next, and anything you need from me.
- When you need a decision from me, speak the question too.
- Keep it short and conversational. Never read code, file paths, logs, or
  long lists aloud. Those stay in text.
- Do not speak for quick back-and-forth or trivial answers.
- If I ask to hear something long, use queue_speech.
- Speak in the language I write in.

3. Get told when Claude needs you. When Claude Code waits for a permission or an answer, the model is not running, so it cannot call speak. Claude Code fires a hook at those moments instead, and paxa say turns the hook into a spoken phrase such as "Permission needed." Put the paxa command on your PATH:

npm install -g @paxalabs/mcp

Then add to ~/.claude/settings.json:

{
  "hooks": {
    "Notification": [
      {
        "matcher": "permission_prompt|idle_prompt|agent_needs_input",
        "hooks": [{ "type": "command", "command": "paxa say" }]
      }
    ]
  }
}

paxa say takes the key from PAXA_API_KEY, or from the paxa entry in ~/.claude.json when that is unset, so step 1 is all the setup it needs. A Stop hook configured the same way speaks "Done." at the end of every turn.

The built-in phrases are synthesized once per voice and kept in your user cache directory (~/Library/Caches/paxa/say on macOS, ~/.cache/paxa/say on Linux, %LOCALAPPDATA%\paxa\cache\say on Windows). After that first play, which costs well under one credit, a notification plays from disk: no network round trip and no credits.

To change the words, write your own text in the hook command and add --cache so it gets the same treatment. One entry per event, since the matcher picks the event:

{
  "hooks": {
    "Notification": [
      {
        "matcher": "permission_prompt",
        "hooks": [{ "type": "command", "command": "paxa say --cache \"Hey, need your OK\"" }]
      },
      {
        "matcher": "idle_prompt|agent_needs_input",
        "hooks": [{ "type": "command", "command": "paxa say --cache --voice cookie \"Your turn\"" }]
      }
    ]
  }
}

Without --cache, nothing you type or pipe into paxa say is written to disk, and messages carried inside a hook payload never are.

On macOS the built-in afplay needs about half a second just to start and stop, which is most of the delay you hear on a short phrase. With brew install mpg123 (or ffmpeg) installed, cached phrases play through that instead: mpg123 starts in about 50 ms, ffplay in about 300 ms.

paxa say also works on its own:

paxa say "Build finished"
paxa say --voice cookie "Deploy is live"

If your editor or desktop app was not launched from a terminal, its PATH may not include your node bin directory, and the hook will fail silently. Use the absolute path to paxa in the hook command if that happens.

Content creation

Three things creators asked for, each the local half of an API call:

• Transcribe a video. Give transcribe_audio an mp4, mov, mkv, or most other containers; ffmpeg pulls the sound track out locally and the API transcribes it. Add pauses_over: 0.7 and the result lists every silence longer than that with its start and end, the dead air to cut. Ask for save: ["srt"] and the captions come back too.
• Voiceover with captions that match. text_to_speech with subtitles: "srt" (or "vtt") writes a caption file next to the audio, timed from the synthesized words. Cues break at sentence punctuation, at pauses, and at the line budget, never inside a word, and Thai lines end where the writer put a space. Timed synthesis bills 1.25x.
• Long narration to one file. Scripts past 5,000 characters are split at paragraphs and sentences, synthesized part by part, and joined with ffmpeg into a single mp3, opus, or wav, captions offset to match.

ffmpeg is the one requirement for video input and for joining parts (brew install ffmpeg on macOS). Everything else works without it.

Listening

listen turns the microphone into an answer. Ask a question with speak, call listen, and the user's spoken reply comes back as text as soon as they stop talking: Paxa's realtime transcription detects the end of the turn, so nothing has to guess at silence. The audio goes straight to the API and is never written to disk. A few seconds of listening costs well under one credit (12.5 credits per minute, silence included).

It needs a command-line recorder, which stock macOS and Windows do not ship: brew install ffmpeg or brew install sox on macOS; sox on Windows (or ffmpeg with PAXA_MIC set to the DirectShow device name); ffmpeg, sox, parecord, or arecord on Linux. It also needs Node 22 or newer, and the app that launched the server (Terminal, VS Code, Claude Desktop) must have microphone permission. PAXA_MIC picks a device when the system default is not the one you want. To check recognition without a microphone, node scripts/listen-file.mjs recording.mp3 feeds a file through the same session.

Environment variables

Variable	Required	Default	Purpose
PAXA_API_KEY	yes		Your API key. The server starts without it, but every tool that calls the API then fails with setup instructions the agent can relay
PAXA_OUTPUT_DIR	no	working directory	Where text_to_speech saves files
PAXA_DEFAULT_VOICE	no	nomyen	Voice used when a tool call does not pick one. Every voice is designed around one language. English text usually sounds best with an English voice (donut, cookie, toast, latte, espresso, mocha), Mandarin with taohuay or oolong
PAXA_VOCABULARY	no		Keyword pinning for transcribe_audio: comma-separated names and terms the transcript should spell as written (product names, people, jargon)
PAXA_DEFAULT_SPEED	no	1	Speaking rate used when a call does not pick one, 0.5 to 1.5. Pitch is preserved and the price is the same; 1.2 to 1.3 suits long reads
PAXA_MIC	no	system default	Microphone device for listen: an AVFoundation device name on macOS, a PulseAudio or ALSA device on Linux, a DirectShow device name on Windows
PAXA_VOCABULARY_FILE	no		A text file with one term per line (# starts a comment), also pinned on every transcription. Read at call time, so edits apply without a restart
PAXA_BASE_URL	no	https://api.paxalabs.com	API origin override

To pin a different list per project, set the vocabulary variables in a project-scope server entry (Claude Code's project scope, .cursor/mcp.json, .vscode/mcp.json). On each call the tool takes the call's own terms first, then the configured ones, deduplicated and cut at the API's limit of 50, and reports how many it pinned.

Playback support

Platform	File player	Streaming player	Pause/resume
macOS	afplay (built in)	mpg123, ffplay, or mpv if installed	yes
Linux	ffplay, mpv, mpg123, paplay, or aplay	mpg123, ffplay, or mpv	yes
Windows	ffplay if installed, else PowerShell (wav)	mpg123, ffplay, or mpv if installed	no

Streaming needs a player that reads from stdin. On macOS, brew install mpg123 (the quickest to start) or ffmpeg enables it; without one, speech still plays through afplay after the download completes. If no player is found at all, speech tools report it clearly and text_to_speech still works.

Claude Desktop extension

Each release on GitHub ships a .mcpb bundle. Download it, open it with Claude Desktop, and enter your API key in the extension settings. The bundle carries its own copy of the server and its dependencies, so it works without Node.js or npm on the machine.

Development

pnpm install
pnpm build        # compile to dist/
pnpm typecheck
pnpm mcpb         # build release/paxalabs-mcp-<version>.mcpb for Claude Desktop

# live smoke test (spends a few credits, plays audio out loud)
PAXA_API_KEY=pxa_... TEST_OUT_DIR=/tmp/paxa-out node scripts/e2e.mjs