Skip to main content
Glama
Hy1ander

NeuroDynamic Audio and LLM APIs

by Hy1ander

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NEURODYNAMIC_STATENoPath to a private state directory used to store purchase history, signed payment proofs, receipts and returned files. Required only for optional purchases.
NEURODYNAMIC_INPUT_DIRNoPath to a separate input directory containing audio files to be uploaded for transcription. Required only for transcription purchases.
NEURODYNAMIC_BUYER_KEY_FILENoPath to a file containing the raw hexadecimal private key of a dedicated low-balance Base wallet, with file mode 0600. Required only for optional purchases.
NEURODYNAMIC_TOTAL_CAP_ATOMICNoCumulative client spending cap in atomic units, e.g. '50000' is 0.05 USDC total. Limited to at most 1 USDC. Required only for optional purchases.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
catalogueA

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

quoteA

Get a free verified USDC/Base quote: narration, transcription, abliterated or abliterated-large. No input uploaded or funds spent.

purchase_jsonA

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.

transcribe_fileA

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.

payment_statusB

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.

budget_statusA

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

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 6 tools

Disambiguation5/5

Each tool maps to a distinct step in the purchase lifecycle: catalogue browsing, quoting, buying JSON-based services, buying file transcription, payment status, and budget status. There is no meaningful overlap between them, and the descriptions clarify the boundaries.

Naming Consistency3/5

Names are readable but mix conventions: read-style tools are bare nouns or noun_noun (catalogue, quote, payment_status, budget_status), while purchase actions use verb_noun (purchase_json, transcribe_file). A uniform get_/list_ or verb_noun pattern would improve consistency.

Tool Count5/5

Six tools is well-scoped for a paid audio/LLM API. Each tool earns its place in the browse-quote-purchase-status workflow without bloat.

Completeness4/5

The core purchase lifecycle is covered: discover services, price them, buy narration/LLM text or transcription, and check payment/budget status. Minor gaps exist, such as no explicit output-retrieval or voice-cloning purchase tool, though output is saved to private state and cloning may be out of scope.

Maintenance

ActivityMaintained
ResponsivenessNo issues