Felona Voice v0.2.0 is now live — Sub-10ms neural voice routing with deterministic state machines.Star on GitHub
FelonaVoicev0.2.0
GitHubStart Building
Docs/Getting Started/Overview & Quickstart
docs/README.md

Overview & Quickstart

docs/README.md

Welcome to Felona Voice — the ultra-low-latency, open-source voice agent framework powered by Joint Embedding Vectors (JEV).

30-Second Quickstart

Install the package from npm and start building in under 30 seconds with zero external API dependencies:

bash
npm install felona-voice

Create your agent with deterministic actions and test a sub-millisecond turn:

typescript
import { createAgent } from "felona-voice";

const agent = createAgent("Concierge")
  .system("You are an upscale hotel concierge.")
  .action("book_table", "Book restaurant reservation", async () => "Table booked for 7 PM!")
  .action("room_service", "Order fresh towels or food", async () => "Room service is on its way.")
  .fallback("Sorry, I am not able to understand that. How may I assist you?");

// 1. Simulate a turn instantly (sub-millisecond):
const reply = await agent.interact("can I get clean towels?");
console.log(reply.text); // "Room service is on its way."

// 2. Export documentation as Markdown:
console.log(agent.drawMarkdown());

// 3. Or start streaming WebSocket voice server:
// agent.listen({ port: 8080 });

Core Concepts at a Glance

1. JEV Neural Routing

Encodes user utterances into a semantic vector space and matches them against candidate actions via cosine similarity in ~5ms.

2. Deterministic & Safe

Actions execute pure TypeScript/JavaScript code, database queries, or tool calls. No hallucinations, no unpredictable prompt drift.

3. Directed State Machines

Build stateful conversational graphs using .addNode(), .addEdge(), and .invoke().

4. Native Visualization

Generate diagrams that render automatically in GitHub, VS Code Markdown preview, and docs platforms with zero extra tools.