NeuroDynamic Audio, Captions, Documents and LLM APIs

tech.neurodynamicPublished by neurodynamic.techv1.1.2Updated Nov 6, 2026

Audio, captions, PDF extraction, image OCR and LLM APIs with capped USDC payments.

VerifiedSTDIODesktop onlyFinanceMedia & DesignAI & ML

Overview

AI-generated overview

Lets an assistant buy capped USDC-paid audio transcription, captions, narration, PDF extraction, image OCR and LLM text through a local wallet.

What you can do
  • Browse the free catalogue of services, voices, schemas and cloning requirements, and get free USDC/Base quotes
  • Buy narration or LLM text, with output saved to a private state directory
  • Buy transcription of a local audio file, or a TXT/SRT/VTT/word-timestamp transcript package
  • Buy raw text and Markdown extraction from a text-native PDF
  • Buy printed-English OCR for a PNG or JPEG image
  • Check saved purchase metadata, payment recovery status and the cumulative client budget
When to use it
Useful when you want an assistant to produce transcripts, caption files, narration, PDF text or image OCR on demand and are willing to pay per call in USDC from a local wallet, rather than holding API accounts with each provider.
Requirements
Runs locally over stdio via uvx from the PyPI package, desktop only. Needs an owner-configured local wallet and budget, plus an owner-configured input directory (NEURODYNAMIC_INPUT_DIR) for file uploads. Purchases require confirm_purchase=true. No authentication or environment variables are declared in the manifest.
Before you install
Purchases spend real USDC from an owner-funded wallet; catalogue and quotes are free but every other tool buys something. Files are uploaded to the merchant only on an explicit purchase. Keep purchase IDs after errors and never invent a replacement, since uncertain payments stay reserved. Uploaded files must sit in the configured input directory with mode 0600. Private voice cloning needs a separate approved-account workflow.

Installation

In SourceWeft

  1. Open NeuroDynamic Audio, Captions, Documents and LLM APIs in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Tools

9

catalogue

Read free services, voices, schema or cloning requirements. No wallet or payment needed.

Parameterskind

quote

Get a free verified USDC/Base quote for an existing service. No input uploaded or funds spent.

Parametersservicerequired

purchase_json

Buy narration or LLM text using an owner-funded local wallet. Read schema and quote first. Supply a unique purchase_id once; reuse it after uncertainty, never invent a replacement. Saves output to the caller's private state directory. Narration body: input, voice. LLM body requires input, adult=true, third_party_processing=true, terms_version=2026-09-11-llm-v1 and optional max_tokens. Only assert these acknowledgements with the user's authority.

Parametersbodyrequiredservicerequiredpurchase_idrequiredconfirm_purchase

transcribe_file

Buy transcription of a caller-provided audio file (60 seconds/12 MiB maximum). Filename must be a basename within owner-configured NEURODYNAMIC_INPUT_DIR; file must be mode 0600. It is uploaded only for an explicit purchase. Never provide a path outside that directory.

Parametersfilenamerequiredlanguagepurchase_idrequiredconfirm_purchase

transcript_package_file

Buy a TXT/SRT/VTT/word-timestamp transcript package for one audio file up to 8 MiB and 60 seconds. No speaker identification, notes or translation.

Parametersfilenamerequiredlanguagepurchase_idrequiredconfirm_purchase

extract_pdf_file

Buy raw text and Markdown extraction from one text-native PDF up to 10 MiB and 20 pages. Scanned PDFs are unsupported.

Parametersfilenamerequiredpurchase_idrequiredconfirm_purchase

ocr_image_file

Buy printed-English OCR for one PNG or JPEG up to 10 MiB and 12 megapixels. Handwriting, layout fidelity and translation are unsupported.

Parametersfilenamerequiredpurchase_idrequiredconfirm_purchase

payment_status

Read saved purchase metadata and, for LLMs, query payment recovery for free. Never signs or pays; cannot restore LLM output the merchant does not retain.

Parameterspurchase_idrequired

budget_status

Read the cumulative client budget. Uncertain purchases remain reserved across restarts.

Takes no parameters.

Version history

4
  1. v1.1.2LatestNov 6, 2026
  2. v1.1.1Nov 5, 2026
  3. v1.0.1Oct 25, 2026
  4. v1.0.0Sep 16, 2026

Score

55% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.