# PUHE

> Puhetta omalla tekoälylläsi. Your voice, your AI. FI/EN voice studio. This document tells an agent how to call it.

## Installation

Nothing to install. This app runs on an AIMEAT node and is reachable two ways.

Over MCP — attach any MCP-capable client to `https://aimeat.io/v1/mcp` (OAuth 2.1), then:

```
    owner:  happydude500001
    app_id: puhe.html        (not "puhe")

aimeat_app_tools_get   { owner: "happydude500001", app_id: "puhe.html" }
```

Over HTTP — get an identity through the RFC 8628 device flow described at `https://aimeat.io/auth.md`, then
call the endpoints in `https://aimeat.io/v1/spec`.

## Configuration

- **Scopes.** The owner approves a scope set when they approve your agent. A call outside it
  answers 403 naming the scope, never an empty result.
- **Payment.** Priced tools answer 402 with the terms attached until a checkout for them completes;
  completing the checkout IS the invocation.
- **Schemas.** Every tool carries a full input and output schema in the manifest, so nothing has to
  be inferred from the app source: `https://aimeat.io/v1/apps/happydude500001/puhe.html/webmcp`

## Usage

```
aimeat_app_tool_invoke {
  owner: "happydude500001",
  app:   "puhe.html",
  tool:  "search",
  input: { ... }
}
```

This app publishes no priced tools.

## What this app does

# PUHE

A Finnish and English voice studio for spoken conversations with your own AIMEAT AI account.

- Open [PUHE](https://puhe.apps.aimeat.io/), sign in and start once. Automatic turns are the default: a pause sends each spoken turn. With speakers, the app finishes its answer before accepting the next turn. Headphone users can enable spoken interruption. Manual speech and text input remain available in settings.
- Choose a response rhythm, recognition model, reply model and speech voice. Export the full configuration as JSON for your own application.
- Interrupt an answer or stop the session and microphone at any time.
- See time to first audio and completion time for each turn.
- Switch interface language without interrupting speech or losing drafts; configure recognition and reply language separately with Spoken language.

The text and voice are AI generated. Submitted turns use the signed-in person's AI provider and budget. Keys remain on the server. The app saves no conversation, audio or configuration on the node; current session state exists only in the open page. Providers and the node maintain their own usage and provenance records.

The app-bound `puhe` skill explains operation and configuration. Headless speech generation is available through the node's `aimeat_voice_reply` and `aimeat_voice_speak` tools; those calls are independent of the browser session and incur AI usage. This public page exposes no person's conversation.


## Agent affordances

- Act — WebMCP tool listing for this app: https://aimeat.io/v1/apps/happydude500001/puhe.html/webmcp
- Learn — skills bound to this app: https://aimeat.io/v1/apps/happydude500001/puhe.html/skills
- App catalog on this node (this app: happydude500001/puhe.html): https://aimeat.io/app-catalog.html
- Register an agent on this node (RFC 8628 device flow): https://aimeat.io/auth.md


## Where the rest is

- [llms.txt](https://puhe.apps.aimeat.io/llms.txt) · [Site map](https://puhe.apps.aimeat.io/sitemap.md)
- [Node manual](https://aimeat.io/llms-full.txt) · [Node glossary](https://aimeat.io/v1/glossary.md) · [OpenAPI](https://aimeat.io/v1/spec)