Skip to content
Agentmart
Submit a tool

Paxa Labs

Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction

Connector by paxalabs.comOfficial · Domain verified by the MCP Registry

IndexedMITLocal (stdio)★ 10
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/paxalabs-com-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction

Use cases: audio-video, translation, document-processing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
5 read · 12 write · 2 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Node.js package

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • get_account
  • list_models
  • list_voices
  • ocr_document
  • translate_to_thai

Write 12 · Create, change, send or run things.

  • control_playback
  • design_voice
  • extract_fields
  • listen
  • play_audio
  • queue_speech
  • refine_voice
  • rename_voice
  • save_voice
  • send_feedback
  • speak
  • transcribe_audio

Delete 2 · Delete, drop, revoke or wipe things.

  • delete_voice
  • text_to_speech

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • PAXA_API_KEY

Other settings (environment variables or headers).

  • PAXA_DEFAULT_VOICE
  • PAXA_OUTPUT_DIR

Files it touches

  • Any path the agent passes to its tools

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • control_playbackPlayback control

    Inspect and control the shared audio queue. status reports what is playing, what is queued, and any synthesis failures. pause and resume halt and continue playback (not supported on Windows). skip drops the current segment. clear stops playback and empties the queue.

  • delete_voiceDelete a designed voicecan change or delete data

    Delete one of the account's designed voices and free its slot. Cannot be undone: every later request in the voice fails, and designing again does not bring the same sound back. Use it only when the user asks to delete that voice. Free.

  • design_voiceDesign a new voice

    Description is built at runtime.

  • extract_fieldsExtract fields from a document

    Extract typed fields from a local PDF, PNG, JPEG, or WebP document (up to 20 pages and 10 MiB) with Paxa Document Extraction. You write a schema of fields; every value returned is text printed in the document, read as the field's type, or null with the reason. Nothing is inferred or looked up. Built for Thai documents (receipts, tax invoices, forms, IDs) and fine on English ones. Costs 13 credits per page for a schema of up to 50 leaf fields and 19.5 per page for 51 to 100; the page reading and the evidence spans cost nothing extra. A schema the API refuses costs nothing and names the field an…

  • get_accountAccount and creditsread-only

    Show the API key's account: credit balance, plan, and rate limits. Free.

  • list_modelsList modelsread-only

    List available Paxa models with their limits and credit pricing. Free.

  • list_voicesList voicesread-only

    List the Paxa TTS voices: the account's designed voices with their slots, then the catalog roster with ids, names, gender, language, and character notes. Free.

  • listenListen to the microphone

    Description is built at runtime.

  • ocr_documentOCR a documentread-only

    Run Paxa OCR on a local PDF, PNG, JPEG, or WebP file and return its content as GitHub-flavored Markdown (or structured blocks). Up to 50 pages and 10 MiB per file. Costs 6.5 credits per page.

  • play_audioPlay an audio file

    Play a local audio file through this machine's speakers, for example a file produced earlier by text_to_speech. Blocks until playback finishes. Free (no API call).

  • queue_speechQueue long-form speech

    Description is built at runtime.

  • refine_voiceRefine a draft voice

    Description is built at runtime.

  • rename_voiceRename a designed voice

    Rename one of the account's designed voices. The id and the sound stay the same, so anything that uses the id keeps working. A catalog voice's name is refused. Free.

  • save_voiceSave a designed voice

    Save a draft from design_voice or refine_voice as one of the account's voices, and get its id (voice_...), which speak, queue_speech, and text_to_speech accept as voice on paxa-tts-flash-v2, for this account only. Save only the draft the user picked. Saving the same draft again returns the same voice and uses no slot. A saved voice's sound never changes: design a new voice for a different sound. The plan sets how many voices the account keeps (Free 1, Starter 3, Standard 10, Pro 50); list_voices shows the slots in use. Free.

  • send_feedbackSend feedback to Paxa

    Report a wrong or poor output, an API problem, or a platform issue to the Paxa Labs team, tied to the request ids the other tools print ("Request id: ..."). A rating alone on at least one request id is a complete report. For a wrong output, add an example with the exact input, the output received, and the output expected. Free, no credits. Use it when the user says an output was wrong, or asks to report a problem; do not file reports the user did not ask for.

Show 4 more tools
  • speakSpeak out loud

    Description is built at runtime.

  • text_to_speechText to speech (file only)can change or delete data

    Description is built at runtime.

  • transcribe_audioTranscribe a recording

    Description is built at runtime.

  • translate_to_thaiTranslate to Thairead-only

    Translate text from any language into Thai with Paxa Translate. Accepts a single string or up to 200 segments that share context. Costs 25 credits per 1000 text characters (minimum 2 credits); context and glossary characters bill at 8 per 1000.

Compare and alternatives

    Featured in

    Signals

    Stars
    10
    Forks
    0
    Open issues
    0
    Weekly downloads
    414
    Last commit
    Oct 18, 2026 (11 days ago)
    Last release
    Oct 18, 2026 (11 days ago)
    Last package publish
    Oct 24, 2026 (5 days ago)

    From GitHub (fetched Oct 24, 2026) and the package registry.

    Details

    Registry name
    com.paxalabs/mcp
    Version
    0.1.0-beta.15
    Auth
    API key
    Packages
    npm @paxalabs/mcp
    License
    MIT
    Repository
    github.com/paxalabs/mcp
    Website
    paxalabs.com/docs
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql
    Cite this page

    Paxa Labs MCP server. Agent Mart. https://agentmart.dev/connectors/paxalabs-com-mcp (last updated 2026-10-24)