VOICE → API · SAFETY-FIRST

Make any API
voiceable.

A spoken word never executes.

Point Voxy at an API spec and get a working voice agent in an afternoon — with the confirmation gate, no-guessing parser, and audit trail already built. The safety is the product: a misheard command never fires a destructive call.

spoken commands are read back   a deliberate click confirms   destructive actions are flagged

Wiring voice to an API means STT, intent parsing, slot resolution, confirmation UX, error recovery, and an audit trail — and then getting the safety right so a mis-parse never charges a card or deletes a deployment. That safety work is the part that quietly sinks these projects. Voxy already solved it. You bring the spec.

THE WORKFLOW

Spec in, safe agent out.

  1. 01

    Point at your spec

    Drop in an OpenAPI 3.x spec. Voxy normalizes it into one API model — operations, typed params, auth scheme, error shapes.

  2. 02

    Review the draft

    It generates a Voice Layer Definition and surfaces every write operation for you to review — destructive flags, read-backs, slots. Human-in-the-loop where it matters.

  3. 03

    Talk to your API

    Speak a command. Hear it read back. Confirm with a click. It executes through the gated runtime, and every step lands in the audit log.

voxy generate resend.json
$ voxy generate resend.json --out resend.vld.json

  draft VLD — Resend (3 write ops to review)
  ┌──────────────┬────────┬───────────┬─────────────┬───────────────────┐
  │ operation    │ method │ path      │ destructive │ reason            │
  ├──────────────┼────────┼───────────┼─────────────┼───────────────────┤
  │ sendEmail    │ POST   │ /emails   │ YES         │ verb-heuristic    │
  │ createDomain │ POST   │ /domains  │ no          │ write — review    │
  │ deleteApiKey │ DELETE │ /api-keys │ YES         │ method:DELETE     │
  └──────────────┴────────┴───────────┴─────────────┴───────────────────┘
  Every write op surfaced for review. Confirm flags before use.
  ✓ wrote draft VLD → resend.vld.json

THE CORE

The safety is the product.

Four invariants, proven on the hardest case — a live trading agent — then lifted out so they hold for any API unchanged.

Manual gate

Execution requires a token that can only be minted by a deliberate gesture — a click, a keystroke. A spoken "confirm" is only a request to confirm. Structurally unforgeable.

No-guessing parse

Strict, schema-conformant tool use. Missing a required slot elicits a question — it never invents a value. Deliberation and venting are caught before any action path.

100% destructive recall

Self-declared hints plus verb/method heuristics flag every irreversible or costly action. Missing one is the catastrophic failure — so detection errs toward flagging.

Event-sourced audit

Every step — heard, parsed, read back, confirmed, executed — is one immutable row. Full session reconstruction, and an alarm on any execute without a matching confirmation.

Battle-tested on a live trading agent — the hardest safety case we could find. See the trading demo →

TWO WAYS TO SHIP

Operate it yourself, or embed it for your users.

MODE A

Run your own API by voice

You operate your own account. Auth is a single token, regulatory exposure is low, the value is personal speed. This is where you start.

  • Local-first, single-token auth
  • Voice in, text out, click to confirm
  • Spec to working agent in an afternoon
MODE B

Embed it for your end-users

Your users operate your API by voice — and never see Voxy. The gate, the secrets, and execution stay server-side. Per-tenant isolation; no credential ever reaches the browser.

  • Hosted runtime + thin client SDK
  • Multi-tenant secret vault, server-side
  • Confirmation is an explicit client click

ONE ENGINE, EVERY DOMAIN

Resend and Vercel are live.
Stripe runs in test. Yours is next.

Give your API a voice.
Keep the safety.

Early access rolls out across the Tier-1 APIs first. Tell us the API you'd point it at — we'll send back a working draft VLD to try.

No spam. Just your draft agent and a note when your tier opens.