Rehearsal Note Whisperer

Required key.

Add this in your Lovable project under Settings → Secrets before pasting the prompt below.

Paste into a fresh Lovable project. Make sure the key above is set first. read the build strategy →

Build "Rehearsal Note Whisperer" as a ONE-SHOT Lovable build. The participant has only
5 credits — this single message must produce a working demo with no follow-ups.
Single-page TanStack Start app. Cut scope ruthlessly.

CONCEPT
Lovable AI synthesizes rehearsal notes so directors give actionable feedback; ElevenLabs delivers personalized critiques gently to each performer's phone.
Discipline: Theater & Live Performance (director actor feedback).
Recipe: Lovable AI brain + ElevenLabs Text-to-Speech (streaming voice) as the voice surface.
Why this voice surface: Private audio delivery allows actors to absorb sensitive directing notes without public embarrassment.

LOVABLE BUDGET (HARD CAP: ONE-SHOT, ~5 CREDITS TOTAL):
The participant has FIVE Lovable credits for the whole build. This prompt MUST
ship a working demo on the FIRST message with zero follow-ups. Engineer for that.
- ONE TanStack Start app, ONE route (`src/routes/index.tsx`). No extra pages, no auth, no nav.
- TWO TanStack server functions max: one for the Lovable AI call (the brain),
  one for the ElevenLabs call (the voice). Fold them into one if the voice
  primitive does not need server-side text generation.
- ONE client surface (a button, a mic, or a prompt box) wired to those server fns.
- NO database, NO Lovable Cloud, NO auth, NO file uploads, NO extra integrations.
- NO tests, NO docs pages, NO settings screens, NO theming toggles.
- Libraries: template defaults + `ai` + `@ai-sdk/openai-compatible` + `zod`,
  plus (only if the voice kernel needs it) `@elevenlabs/react`. Nothing else.
- Keep the diff small enough to land in one build pass. If a feature is not on
  screen in the user flow below, do not build it. Cut scope before adding scope.

STACK
- TanStack Start app, the index route only.
- Lovable AI Gateway (the brain) + ElevenLabs (the voice). All calls live
  inside `createServerFn` handlers so both keys stay on the server.
- Client surface fits the kernel: a prompt box for TTS / music / SFX, a mic
  for agents, a live caption strip for scribe. Render markdown from the brain
  with `react-markdown` if you show the text on screen.
- Tailwind + shadcn. Editorial look: gold accent on a dark or warm-cream
  background, generous type, one strong headline, one primary action.
- Footer renders: "Built during the Creative AI & Quantum Hackathon organised by StreetKode Fam during Indian Krump Festival 14".

BRAIN — Lovable AI Gateway (free for participants, no key prompt needed):
```ts
// src/lib/ai-gateway.server.ts
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
export function gateway() {
  return createOpenAICompatible({
    name: "lovable",
    baseURL: "https://ai.gateway.lovable.dev/v1",
    headers: {
      "Lovable-API-Key": process.env.LOVABLE_API_KEY!,
      "X-Lovable-AIG-SDK": "vercel-ai-sdk",
    },
  });
}
```
Default model: `google/gemini-3-flash-preview`. Use `generateText` (or
`streamText` for long output) from `ai`. Keep prompts and model calls inside
the server function — never call the gateway from client code.

SERVER FUNCTION (src/lib/coach.functions.ts) — brain + voice in one call:
```ts
import { createServerFn } from "@tanstack/react-start";
import { generateText } from "ai";
import { z } from "zod";
import { gateway } from "./ai-gateway.server";

/** Built during the Creative AI & Quantum Hackathon organised by StreetKode Fam during Indian Krump Festival 14 */
export const speakAdvice = createServerFn({ method: "POST" })
  .inputValidator((d) => z.object({
    topic: z.string().min(1).max(500),
    language: z.string().default("English"),
  }).parse(d))
  .handler(async ({ data }) => {
    // 1. BRAIN — Lovable AI writes the answer for the director actor feedback use case.
    const { text } = await generateText({
      model: gateway()("google/gemini-3-flash-preview"),
      system: `You are an expert helper for director actor feedback. Answer in ${data.language}. ` +
              `Keep it warm, specific, under 120 words. Markdown is fine but no headings.`,
      prompt: data.topic,
    });

    // 2. VOICE — ElevenLabs reads it back in the chosen language.
    const isEn = data.language === "English";
    const r = await fetch(
      "https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb/stream" +
        "?output_format=mp3_44100_128",
      {
        method: "POST",
        headers: { "xi-api-key": process.env.ELEVENLABS_API_KEY!, "Content-Type": "application/json" },
        body: JSON.stringify({
          text,
          model_id: isEn ? "eleven_turbo_v2_5" : "eleven_multilingual_v2",
        }),
      },
    );
    if (!r.ok) throw new Error(`TTS failed: ${r.status}`);
    const buf = await r.arrayBuffer();
    return { text, audio: Buffer.from(buf).toString("base64") };
  });
```

CLIENT (in the page component):
```tsx
import { useServerFn } from "@tanstack/react-start";
import { speakAdvice } from "@/lib/coach.functions";

const ask = useServerFn(speakAdvice);
const onSubmit = async (topic: string, language: string) => {
  const { text, audio } = await ask({ data: { topic, language } });
  // render `text` on screen with react-markdown, then:
  await new Audio(`data:audio/mpeg;base64,${audio}`).play();
};
```

Voice: George (`JBFqnCBsd6RMkjVDRZzb`). Swap from https://elevenlabs.io/voice-library.

TRANSLATION — included by default:
Add a language `<Select>` to the UI (English, Español, Français, Deutsch,
Português, हिंदी, 日本語). Before sending the AI output to ElevenLabs,
ask the gateway to translate it into the chosen language in the same server
function. Then pass the translated text to ElevenLabs with
`model_id: "eleven_multilingual_v2"` so the voice speaks naturally in that
language. Default the select to English so the demo works without a click.

USER FLOW (the entire app — nothing else exists)
1. Land on the page; the headline previews what the demo does for director actor feedback.
2. The primary action (a 'play' button (or auto-play) that streams lifelike narration of any text the app generates) is one tap away; the rest of the layout supports it.
3. Lovable AI does the thinking, ElevenLabs handles the voice surface, and the
   result (audio + any text) stays on screen so the user can retry or share.

KEYS — both already provided to participants for free:
1. `LOVABLE_API_KEY` (the AI brain). Auto-injected in every Lovable project.
   Read it only on the server via `process.env.LOVABLE_API_KEY`. Never prefix
   with `VITE_` and never expose to the client.
2. `ELEVENLABS_API_KEY` (the voice). Best path: ask Lovable to connect the
   ElevenLabs standard connector — it syncs the key automatically and rotates
   from the dashboard. Fallback: paste a key from
   https://elevenlabs.io/app/settings/api-keys into Project Settings -> Secrets.
   Read it only on the server, header `xi-api-key`, never prefix with `VITE_`.

CREDIT (must appear in UI footer AND as JSDoc on the server function):
Built during the Creative AI & Quantum Hackathon organised by StreetKode Fam during Indian Krump Festival 14

Market sizing.

Indicative figures for hackathon pitches — refine with your own research before raising.