working with voice tts

.gitignore

@@ -0,0 +1,41 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/versions
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# env files (can opt-in for committing if needed)
+.env*
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts

README.md

@@ -0,0 +1,36 @@
+This is a [Next.js](https://nextjs.org) project bootstrapped with [`create-next-app`](https://nextjs.org/docs/app/api-reference/cli/create-next-app).
+
+## Getting Started
+
+First, run the development server:
+
+```bash
+npm run dev
+# or
+yarn dev
+# or
+pnpm dev
+# or
+bun dev
+```
+
+Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
+
+You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
+
+This project uses [`next/font`](https://nextjs.org/docs/app/building-your-application/optimizing/fonts) to automatically optimize and load [Geist](https://vercel.com/font), a new font family for Vercel.
+
+## Learn More
+
+To learn more about Next.js, take a look at the following resources:
+
+- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
+- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
+
+You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js) - your feedback and contributions are welcome!
+
+## Deploy on Vercel
+
+The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js.
+
+Check out our [Next.js deployment documentation](https://nextjs.org/docs/app/building-your-application/deploying) for more details.

eslint.config.mjs

@@ -0,0 +1,18 @@
+import { defineConfig, globalIgnores } from "eslint/config";
+import nextVitals from "eslint-config-next/core-web-vitals";
+import nextTs from "eslint-config-next/typescript";
+
+const eslintConfig = defineConfig([
+  ...nextVitals,
+  ...nextTs,
+  // Override default ignores of eslint-config-next.
+  globalIgnores([
+    // Default ignores of eslint-config-next:
+    ".next/**",
+    "out/**",
+    "build/**",
+    "next-env.d.ts",
+  ]),
+]);
+
+export default eslintConfig;

next.config.ts

@@ -0,0 +1,21 @@
+// next.config.ts
+import type { NextConfig } from "next";
+
+const nextConfig: NextConfig = {
+  turbopack: {
+    // Turbopack handles WASM and workers natively — no extra rules needed
+  },
+  async headers() {
+    return [
+      {
+        source: "/(.*)",
+        headers: [
+          { key: "Cross-Origin-Opener-Policy", value: "same-origin" },
+          { key: "Cross-Origin-Embedder-Policy", value: "require-corp" },
+        ],
+      },
+    ];
+  },
+};
+
+export default nextConfig;

package.json

@@ -0,0 +1,28 @@
+{
+  "name": "nail",
+  "version": "0.1.0",
+  "private": true,
+  "scripts": {
+    "dev": "next dev --webpack",
+    "build": "next build",
+    "start": "next start",
+    "lint": "eslint"
+  },
+  "dependencies": {
+    "@huggingface/transformers": "^3.8.1",
+    "next": "16.2.1",
+    "openai": "^6.33.0",
+    "react": "19.2.4",
+    "react-dom": "19.2.4"
+  },
+  "devDependencies": {
+    "@tailwindcss/postcss": "^4",
+    "@types/node": "^20.19.37",
+    "@types/react": "^19",
+    "@types/react-dom": "^19",
+    "eslint": "^9",
+    "eslint-config-next": "16.2.1",
+    "tailwindcss": "^4",
+    "typescript": "^5"
+  }
+}

postcss.config.mjs

@@ -0,0 +1,7 @@
+const config = {
+  plugins: {
+    "@tailwindcss/postcss": {},
+  },
+};
+
+export default config;

public/file.svg

@@ -0,0 +1 @@
+<svg fill="none" viewBox="0 0 16 16" xmlns="http://www.w3.org/2000/svg"><path d="M14.5 13.5V5.41a1 1 0 0 0-.3-.7L9.8.29A1 1 0 0 0 9.08 0H1.5v13.5A2.5 2.5 0 0 0 4 16h8a2.5 2.5 0 0 0 2.5-2.5m-1.5 0v-7H8v-5H3v12a1 1 0 0 0 1 1h8a1 1 0 0 0 1-1M9.5 5V2.12L12.38 5zM5.13 5h-.62v1.25h2.12V5zm-.62 3h7.12v1.25H4.5zm.62 3h-.62v1.25h7.12V11z" clip-rule="evenodd" fill="#666" fill-rule="evenodd"/></svg>

public/globe.svg

@@ -0,0 +1 @@
+<svg fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><g clip-path="url(#a)"><path fill-rule="evenodd" clip-rule="evenodd" d="M10.27 14.1a6.5 6.5 0 0 0 3.67-3.45q-1.24.21-2.7.34-.31 1.83-.97 3.1M8 16A8 8 0 1 0 8 0a8 8 0 0 0 0 16m.48-1.52a7 7 0 0 1-.96 0H7.5a4 4 0 0 1-.84-1.32q-.38-.89-.63-2.08a40 40 0 0 0 3.92 0q-.25 1.2-.63 2.08a4 4 0 0 1-.84 1.31zm2.94-4.76q1.66-.15 2.95-.43a7 7 0 0 0 0-2.58q-1.3-.27-2.95-.43a18 18 0 0 1 0 3.44m-1.27-3.54a17 17 0 0 1 0 3.64 39 39 0 0 1-4.3 0 17 17 0 0 1 0-3.64 39 39 0 0 1 4.3 0m1.1-1.17q1.45.13 2.69.34a6.5 6.5 0 0 0-3.67-3.44q.65 1.26.98 3.1M8.48 1.5l.01.02q.41.37.84 1.31.38.89.63 2.08a40 40 0 0 0-3.92 0q.25-1.2.63-2.08a4 4 0 0 1 .85-1.32 7 7 0 0 1 .96 0m-2.75.4a6.5 6.5 0 0 0-3.67 3.44 29 29 0 0 1 2.7-.34q.31-1.83.97-3.1M4.58 6.28q-1.66.16-2.95.43a7 7 0 0 0 0 2.58q1.3.27 2.95.43a18 18 0 0 1 0-3.44m.17 4.71q-1.45-.12-2.69-.34a6.5 6.5 0 0 0 3.67 3.44q-.65-1.27-.98-3.1" fill="#666"/></g><defs><clipPath id="a"><path fill="#fff" d="M0 0h16v16H0z"/></clipPath></defs></svg>

public/next.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 394 80"><path fill="#000" d="M262 0h68.5v12.7h-27.2v66.6h-13.6V12.7H262V0ZM149 0v12.7H94v20.4h44.3v12.6H94v21h55v12.6H80.5V0h68.7zm34.3 0h-17.8l63.8 79.4h17.9l-32-39.7 32-39.6h-17.9l-23 28.6-23-28.6zm18.3 56.7-9-11-27.1 33.7h17.8l18.3-22.7z"/><path fill="#000" d="M81 79.3 17 0H0v79.3h13.6V17l50.2 62.3H81Zm252.6-.4c-1 0-1.8-.4-2.5-1s-1.1-1.6-1.1-2.6.3-1.8 1-2.5 1.6-1 2.6-1 1.8.3 2.5 1a3.4 3.4 0 0 1 .6 4.3 3.7 3.7 0 0 1-3 1.8zm23.2-33.5h6v23.3c0 2.1-.4 4-1.3 5.5a9.1 9.1 0 0 1-3.8 3.5c-1.6.8-3.5 1.3-5.7 1.3-2 0-3.7-.4-5.3-1s-2.8-1.8-3.7-3.2c-.9-1.3-1.4-3-1.4-5h6c.1.8.3 1.6.7 2.2s1 1.2 1.6 1.5c.7.4 1.5.5 2.4.5 1 0 1.8-.2 2.4-.6a4 4 0 0 0 1.6-1.8c.3-.8.5-1.8.5-3V45.5zm30.9 9.1a4.4 4.4 0 0 0-2-3.3 7.5 7.5 0 0 0-4.3-1.1c-1.3 0-2.4.2-3.3.5-.9.4-1.6 1-2 1.6a3.5 3.5 0 0 0-.3 4c.3.5.7.9 1.3 1.2l1.8 1 2 .5 3.2.8c1.3.3 2.5.7 3.7 1.2a13 13 0 0 1 3.2 1.8 8.1 8.1 0 0 1 3 6.5c0 2-.5 3.7-1.5 5.1a10 10 0 0 1-4.4 3.5c-1.8.8-4.1 1.2-6.8 1.2-2.6 0-4.9-.4-6.8-1.2-2-.8-3.4-2-4.5-3.5a10 10 0 0 1-1.7-5.6h6a5 5 0 0 0 3.5 4.6c1 .4 2.2.6 3.4.6 1.3 0 2.5-.2 3.5-.6 1-.4 1.8-1 2.4-1.7a4 4 0 0 0 .8-2.4c0-.9-.2-1.6-.7-2.2a11 11 0 0 0-2.1-1.4l-3.2-1-3.8-1c-2.8-.7-5-1.7-6.6-3.2a7.2 7.2 0 0 1-2.4-5.7 8 8 0 0 1 1.7-5 10 10 0 0 1 4.3-3.5c2-.8 4-1.2 6.4-1.2 2.3 0 4.4.4 6.2 1.2 1.8.8 3.2 2 4.3 3.4 1 1.4 1.5 3 1.5 5h-5.8z"/></svg>

public/vercel.svg

@@ -0,0 +1 @@
+<svg fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1155 1000"><path d="m577.3 0 577.4 1000H0z" fill="#fff"/></svg>

public/window.svg

@@ -0,0 +1 @@
+<svg fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"><path fill-rule="evenodd" clip-rule="evenodd" d="M1.5 2.5h13v10a1 1 0 0 1-1 1h-11a1 1 0 0 1-1-1zM0 1h16v11.5a2.5 2.5 0 0 1-2.5 2.5h-11A2.5 2.5 0 0 1 0 12.5zm3.75 4.5a.75.75 0 1 0 0-1.5.75.75 0 0 0 0 1.5M7 4.75a.75.75 0 1 1-1.5 0 .75.75 0 0 1 1.5 0m1.75.75a.75.75 0 1 0 0-1.5.75.75 0 0 0 0 1.5" fill="#666"/></svg>

src/app/api/chat/route.ts

@@ -0,0 +1,31 @@
+// src/app/api/chat/route.ts
+import { NextRequest } from "next/server";
+
+export async function POST(req: NextRequest) {
+  const { messages } = await req.json();
+
+  const res = await fetch(
+    `${process.env.OPENCLAW_BASE_URL}/v1/chat/completions`,
+    {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({
+        model: `openclaw:${process.env.OPENCLAW_AGENT_ID}`,
+        messages,
+        stream: true,
+      }),
+    }
+  );
+
+  if (!res.ok || !res.body) {
+    return new Response(`OpenClaw error: ${res.status}`, { status: 502 });
+  }
+
+  return new Response(res.body, {
+    headers: {
+      "Content-Type": "text/event-stream",
+      "Cache-Control": "no-cache",
+      Connection: "keep-alive",
+    },
+  });
+}

src/app/api/transcribe/route.ts

@@ -0,0 +1,29 @@
+import { NextRequest, NextResponse } from "next/server";
+import { pipeline } from "@huggingface/transformers";
+
+let transcriber: Awaited<ReturnType<typeof pipeline>> | null = null;
+
+async function getTranscriber() {
+  if (!transcriber) {
+    transcriber = await pipeline(
+      "automatic-speech-recognition",
+      "Xenova/whisper-tiny.en",
+      { dtype: "q8" }
+    );
+  }
+  return transcriber;
+}
+
+export async function POST(req: NextRequest) {
+  const { audio } = await req.json();
+  try {
+    const t = await getTranscriber();
+    const result = await (t as any)(Float32Array.from(audio), {
+      chunk_length_s: 30,
+    });
+    return NextResponse.json({ text: result.text?.trim() ?? "" });
+  } catch (err) {
+    console.error("Whisper error:", err);
+    return NextResponse.json({ error: "Transcription failed" }, { status: 500 });
+  }
+}

src/app/globals.css

@@ -0,0 +1,26 @@
+@import "tailwindcss";
+
+:root {
+  --background: #ffffff;
+  --foreground: #171717;
+}
+
+@theme inline {
+  --color-background: var(--background);
+  --color-foreground: var(--foreground);
+  --font-sans: var(--font-geist-sans);
+  --font-mono: var(--font-geist-mono);
+}
+
+@media (prefers-color-scheme: dark) {
+  :root {
+    --background: #0a0a0a;
+    --foreground: #ededed;
+  }
+}
+
+body {
+  background: var(--background);
+  color: var(--foreground);
+  font-family: Arial, Helvetica, sans-serif;
+}

src/app/layout.tsx

@@ -0,0 +1,33 @@
+import type { Metadata } from "next";
+import { Geist, Geist_Mono } from "next/font/google";
+import "./globals.css";
+
+const geistSans = Geist({
+  variable: "--font-geist-sans",
+  subsets: ["latin"],
+});
+
+const geistMono = Geist_Mono({
+  variable: "--font-geist-mono",
+  subsets: ["latin"],
+});
+
+export const metadata: Metadata = {
+  title: "Create Next App",
+  description: "Generated by create next app",
+};
+
+export default function RootLayout({
+  children,
+}: Readonly<{
+  children: React.ReactNode;
+}>) {
+  return (
+    <html
+      lang="en"
+      className={`${geistSans.variable} ${geistMono.variable} h-full antialiased`}
+    >
+      <body className="min-h-full flex flex-col">{children}</body>
+    </html>
+  );
+}

src/app/page.tsx

@@ -0,0 +1,156 @@
+// src/app/page.tsx
+"use client";
+import { useState, useRef, useEffect } from "react";
+import { useChat } from "@/hooks/useChat";
+import { useWhisper } from "@/hooks/useWhisper";
+import { useVoiceRecorder } from "@/hooks/useVoiceRecorder";
+import { stopSpeaking } from "@/lib/tts";
+
+export default function Home() {
+  const [textInput, setTextInput] = useState("");
+  const { messages, isLoading, sendMessage } = useChat();
+  const { status: whisperStatus, modelMessage, transcribe } = useWhisper();
+  const { isRecording, startRecording, stopRecording } = useVoiceRecorder();
+  const bottomRef = useRef<HTMLDivElement>(null);
+
+  useEffect(() => {
+    bottomRef.current?.scrollIntoView({ behavior: "smooth" });
+  }, [messages]);
+
+  const handleTextSubmit = (e: React.FormEvent) => {
+    e.preventDefault();
+    if (!textInput.trim()) return;
+    sendMessage(textInput, "text");
+    setTextInput("");
+  };
+
+  const handlePTTDown = async () => {
+    if (whisperStatus !== "ready") return;
+    stopSpeaking();
+    await startRecording();
+  };
+
+  const handlePTTUp = async () => {
+    if (!isRecording) return;
+    const audioData = await stopRecording();
+    const text = await transcribe(audioData);
+    if (text) sendMessage(text, "voice");
+  };
+
+  const pttDisabled =
+    whisperStatus !== "ready" || isLoading;
+
+  const pttLabel = () => {
+    if (whisperStatus === "loading") return "⏳";
+    if (whisperStatus === "transcribing") return "💬";
+    if (isRecording) return "🔴";
+    return "🎙";
+  };
+
+  const statusLine = () => {
+    if (whisperStatus === "loading") return modelMessage;
+    if (whisperStatus === "transcribing") return "Transcribing on-device…";
+    if (isRecording) return "Recording… release to send";
+    if (whisperStatus === "ready") return "Hold to talk — Whisper ready ✓";
+    return "Initialising Whisper…";
+  };
+
+  return (
+    <main className="flex flex-col h-screen bg-gray-950 text-white">
+      {/* Header */}
+      <header className="flex items-center gap-3 px-6 py-4 border-b border-gray-800 bg-gray-900">
+        <span className="text-2xl">🦞</span>
+        <div>
+          <h1 className="text-xl font-bold tracking-tight">OpenClaw Voice</h1>
+          <p className="text-xs text-gray-500">On-device Whisper · No API keys</p>
+        </div>
+        <span
+          className={`ml-auto w-2 h-2 rounded-full ${
+            whisperStatus === "ready" ? "bg-green-400" : "bg-yellow-400 animate-pulse"
+          }`}
+        />
+      </header>
+
+      {/* Messages */}
+      <div className="flex-1 overflow-y-auto px-4 py-6 space-y-4">
+        {messages.length === 0 && (
+          <div className="text-center mt-20 space-y-2">
+            <p className="text-gray-500 text-sm">
+              {whisperStatus === "ready"
+                ? "Whisper loaded. Hold the button to talk or type below."
+                : modelMessage || "Loading Whisper model…"}
+            </p>
+          </div>
+        )}
+        {messages.map((msg) => (
+          <div
+            key={msg.id}
+            className={`flex ${msg.role === "user" ? "justify-end" : "justify-start"}`}
+          >
+            <div
+              className={`max-w-[75%] rounded-2xl px-4 py-3 text-sm leading-relaxed ${
+                msg.role === "user"
+                  ? "bg-indigo-600 text-white rounded-br-sm"
+                  : "bg-gray-800 text-gray-100 rounded-bl-sm"
+              }`}
+            >
+              {msg.source === "voice" && (
+                <span className="text-xs opacity-40 block mb-1">
+                  {msg.role === "user" ? "🎙 transcribed" : "🔊 spoken"}
+                </span>
+              )}
+              {msg.content || <span className="opacity-40 animate-pulse">▍</span>}
+            </div>
+          </div>
+        ))}
+        <div ref={bottomRef} />
+      </div>
+
+      {/* Controls */}
+      <div className="border-t border-gray-800 bg-gray-900 px-4 py-4 space-y-3">
+        {/* PTT Button */}
+        <div className="flex justify-center">
+          <button
+            onMouseDown={handlePTTDown}
+            onMouseUp={handlePTTUp}
+            onTouchStart={(e) => { e.preventDefault(); handlePTTDown(); }}
+            onTouchEnd={handlePTTUp}
+            disabled={pttDisabled}
+            className={`w-20 h-20 rounded-full text-3xl font-bold transition-all shadow-lg select-none
+              ${isRecording
+                ? "bg-red-500 scale-110 shadow-red-500/40 animate-pulse"
+                : whisperStatus === "transcribing"
+                ? "bg-yellow-500 cursor-wait"
+                : pttDisabled
+                ? "bg-gray-700 cursor-not-allowed opacity-50"
+                : "bg-indigo-600 hover:bg-indigo-500 active:scale-95 cursor-pointer"
+              }`}
+          >
+            {pttLabel()}
+          </button>
+        </div>
+
+        <p className="text-center text-xs text-gray-500">{statusLine()}</p>
+
+        {/* Text Input */}
+        <form onSubmit={handleTextSubmit} className="flex gap-2">
+          <input
+            type="text"
+            value={textInput}
+            onChange={(e) => setTextInput(e.target.value)}
+            placeholder="Or type a message…"
+            disabled={isLoading || isRecording}
+            className="flex-1 bg-gray-800 rounded-xl px-4 py-2 text-sm outline-none focus:ring-2 focus:ring-indigo-500 disabled:opacity-50"
+          />
+          <button
+            type="submit"
+            disabled={isLoading || !textInput.trim()}
+            className="bg-indigo-600 hover:bg-indigo-500 disabled:opacity-40 px-4 py-2 rounded-xl text-sm font-medium transition"
+          >
+            Send
+          </button>
+        </form>
+      </div>
+    </main>
+  );
+}

src/hooks/useChat.ts

@@ -0,0 +1,74 @@
+// src/hooks/useChat.ts
+"use client";
+import { useState, useCallback, useRef } from "react";
+import { Message } from "@/lib/types";
+import { speak } from "@/lib/tts";
+
+export function useChat() {
+  const [messages, setMessages] = useState<Message[]>([]);
+  const [isLoading, setIsLoading] = useState(false);
+  const historyRef = useRef<{ role: string; content: string }[]>([]);
+
+  const sendMessage = useCallback(
+    async (content: string, source: "voice" | "text" = "text") => {
+      if (!content.trim()) return;
+
+      const userMsg: Message = {
+        id: crypto.randomUUID(),
+        role: "user",
+        content,
+        source,
+        timestamp: new Date(),
+      };
+      setMessages((prev) => [...prev, userMsg]);
+      historyRef.current.push({ role: "user", content });
+
+      const assistantId = crypto.randomUUID();
+      setMessages((prev) => [
+        ...prev,
+        { id: assistantId, role: "assistant", content: "", source, timestamp: new Date() },
+      ]);
+      setIsLoading(true);
+
+      try {
+        const res = await fetch("/api/chat", {
+          method: "POST",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify({ messages: historyRef.current }),
+        });
+
+        const reader = res.body!.getReader();
+        const decoder = new TextDecoder();
+        let fullText = "";
+
+        while (true) {
+          const { done, value } = await reader.read();
+          if (done) break;
+
+          for (const line of decoder.decode(value).split("\n")) {
+            if (!line.startsWith("data: ")) continue;
+            const json = line.slice(6).trim();
+            if (json === "[DONE]") continue;
+            try {
+              const delta = JSON.parse(json).choices?.[0]?.delta?.content ?? "";
+              fullText += delta;
+              setMessages((prev) =>
+                prev.map((m) =>
+                  m.id === assistantId ? { ...m, content: fullText } : m
+                )
+              );
+            } catch {}
+          }
+        }
+
+        historyRef.current.push({ role: "assistant", content: fullText });
+        if (source === "voice") speak(fullText);
+      } finally {
+        setIsLoading(false);
+      }
+    },
+    []
+  );
+
+  return { messages, isLoading, sendMessage };
+}

src/hooks/useVoiceRecorder.ts

@@ -0,0 +1,46 @@
+// src/hooks/useVoiceRecorder.ts
+"use client";
+import { useRef, useState, useCallback } from "react";
+
+export function useVoiceRecorder() {
+  const [isRecording, setIsRecording] = useState(false);
+  const mediaRecorderRef = useRef<MediaRecorder | null>(null);
+  const chunksRef = useRef<Blob[]>([]);
+
+  const startRecording = useCallback(async () => {
+    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+    const recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
+    chunksRef.current = [];
+    recorder.ondataavailable = (e) => {
+      if (e.data.size > 0) chunksRef.current.push(e.data);
+    };
+    mediaRecorderRef.current = recorder;
+    recorder.start(250);
+    setIsRecording(true);
+  }, []);
+
+  // Returns a Float32Array that Transformers.js natively accepts
+  const stopRecording = useCallback((): Promise<Float32Array> => {
+    return new Promise((resolve, reject) => {
+      const recorder = mediaRecorderRef.current;
+      if (!recorder) return reject("No recorder active");
+
+      recorder.onstop = async () => {
+        recorder.stream.getTracks().forEach((t) => t.stop());
+        setIsRecording(false);
+
+        const blob = new Blob(chunksRef.current, { type: "audio/webm" });
+        const arrayBuffer = await blob.arrayBuffer();
+        const audioCtx = new AudioContext({ sampleRate: 16000 });
+        const decoded = await audioCtx.decodeAudioData(arrayBuffer);
+
+        // Whisper expects mono 16kHz Float32Array
+        resolve(decoded.getChannelData(0));
+      };
+
+      recorder.stop();
+    });
+  }, []);
+
+  return { isRecording, startRecording, stopRecording };
+}

src/hooks/useWhisper.ts

@@ -0,0 +1,29 @@
+// src/hooks/useWhisper.ts
+"use client";
+import { useState, useCallback } from "react";
+import { WhisperStatus } from "@/lib/types";
+
+export function useWhisper() {
+  const [status, setStatus] = useState<WhisperStatus>("ready");
+  const [modelMessage, setModelMessage] = useState("");
+
+  const transcribe = useCallback(async (audio: Float32Array): Promise<string> => {
+    setStatus("transcribing");
+    try {
+      const res = await fetch("/api/transcribe", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ audio: Array.from(audio) }),
+      });
+      const data = await res.json();
+      return data.text ?? "";
+    } catch (err) {
+      console.error("Transcription error:", err);
+      return "";
+    } finally {
+      setStatus("ready");
+    }
+  }, []);
+
+  return { status, modelMessage, transcribe };
+}

src/lib/tts.ts

@@ -0,0 +1,33 @@
+// src/lib/tts.ts
+export function speak(text: string, onEnd?: () => void): void {
+  if (typeof window === "undefined" || !window.speechSynthesis) return;
+  window.speechSynthesis.cancel();
+
+  const utterance = new SpeechSynthesisUtterance(text);
+  utterance.rate = 1.05;
+  utterance.pitch = 1.0;
+
+  // Wait for voices to load (Safari needs this)
+  const trySpeak = () => {
+    const voices = window.speechSynthesis.getVoices();
+    const preferred = voices.find(
+      (v) =>
+        v.name.includes("Samantha") ||
+        v.name.includes("Google UK English Female") ||
+        v.name.includes("Google US English")
+    );
+    if (preferred) utterance.voice = preferred;
+    if (onEnd) utterance.onend = onEnd;
+    window.speechSynthesis.speak(utterance);
+  };
+
+  if (window.speechSynthesis.getVoices().length > 0) {
+    trySpeak();
+  } else {
+    window.speechSynthesis.onvoiceschanged = trySpeak;
+  }
+}
+
+export function stopSpeaking(): void {
+  window.speechSynthesis?.cancel();
+}

src/lib/types.ts

@@ -0,0 +1,15 @@
+// src/lib/types.ts
+export interface Message {
+  id: string;
+  role: "user" | "assistant";
+  content: string;
+  source?: "voice" | "text";
+  timestamp: Date;
+}
+
+export type WhisperStatus =
+  | "idle"
+  | "loading"
+  | "ready"
+  | "recording"
+  | "transcribing";

tsconfig.json

@@ -0,0 +1,34 @@
+{
+  "compilerOptions": {
+    "target": "ES2017",
+    "lib": ["dom", "dom.iterable", "esnext"],
+    "allowJs": true,
+    "skipLibCheck": true,
+    "strict": true,
+    "noEmit": true,
+    "esModuleInterop": true,
+    "module": "esnext",
+    "moduleResolution": "bundler",
+    "resolveJsonModule": true,
+    "isolatedModules": true,
+    "jsx": "react-jsx",
+    "incremental": true,
+    "plugins": [
+      {
+        "name": "next"
+      }
+    ],
+    "paths": {
+      "@/*": ["./src/*"]
+    }
+  },
+  "include": [
+    "next-env.d.ts",
+    "**/*.ts",
+    "**/*.tsx",
+    ".next/types/**/*.ts",
+    ".next/dev/types/**/*.ts",
+    "**/*.mts"
+  ],
+  "exclude": ["node_modules"]
+}