Fitting Room Murmur

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 "Fitting Room Murmur" 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 scripts a client consultation so the stylist rehearses; Fish Audio generates ambient fitting room murmur and pin-drop SFX.
Discipline: Fashion & Textile Design (stylist roleplay training).
Recipe: Lovable AI brain + Voice Design & Cloning (custom voices) as the voice surface.
Why this voice surface: Designed and cloned voices match stylist roleplay training because Fashion & Textile Design lives or dies on who is speaking — the demo needs its own timbre, invented in seconds, not a stock-voice dropdown.

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 Fish Audio 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`.
  Fish Audio is plain `fetch` — do NOT install an audio SDK.
- 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) + Fish Audio (the voice). All calls live
  inside `createServerFn` handlers so both keys stay on the server.
- Client surface fits the kernel: a prompt box for narration and voice design,
  a mic button for the voice loop, a live caption strip for transcription.
  Render markdown from the brain with `react-markdown` if you show the text.
- 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.

FISH AUDIO NOTES (read before writing the fetch call):
- Base URL `https://api.fish.audio`. Auth is `Authorization: Bearer <key>`.
- The TTS backend is chosen with a REQUEST HEADER, not a body field:
  `model: s2.1-pro`. (`s2.1-pro-free` is the same model at $0 for prototyping; `s1` is legacy.)
- `POST /v1/tts` takes JSON and returns RAW AUDIO BYTES, not JSON. Read it with
  `await res.arrayBuffer()` and base64 it with `Buffer.from(buf).toString("base64")`.
- Body fields: `text` (required), `format` ("mp3" | "wav" | "pcm" | "opus"),
  `mp3_bitrate` (64 | 128 | 192), `sample_rate`, `prosody: { speed, volume }`,
  and `reference_id` to speak in a specific voice model. Omit `reference_id`
  to use the default voice — that is the right call for a one-shot demo.
- `POST /v1/asr` takes `multipart/form-data` (`audio` file, optional `language`,
  `ignore_timestamps=false` for segment times) and returns JSON
  `{ text, duration, segments: [{ text, start, end }] }`.
- Errors come back as `{ "message": "...", "status": 401 }`. Always check
  `res.ok` and surface `res.status` plus a short slice of the body.

SERVER FUNCTION (src/lib/voice.functions.ts) — invent a voice, then speak in it:
```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 designVoices = createServerFn({ method: "POST" })
  .inputValidator((d) => z.object({ vibe: z.string().min(1).max(300) }).parse(d))
  .handler(async ({ data }) => {
    // 1. BRAIN — Lovable AI turns a loose vibe into a precise casting brief
    //    (age, accent, texture, pacing, emotional register) for stylist roleplay training.
    const { text: instruction } = await generateText({
      model: gateway()("google/gemini-3-flash-preview"),
      system: `You are a casting director for stylist roleplay training. Turn the user's vibe into ` +
              `one sentence describing a voice: age, accent, texture, pace, mood. No preamble.`,
      prompt: data.vibe,
    });

    // 2. VOICE — Fish Audio designs candidate voices. Note the special model header.
    const r = await fetch("https://api.fish.audio/v1/voice-design", {
      method: "POST",
      headers: {
        Authorization: `Bearer ${process.env.FISH_AUDIO_API_KEY!}`,
        "Content-Type": "application/json",
        model: "voice-design-1",
      },
      body: JSON.stringify({
        instruction,
        reference_text: "This is how the voice sounds in your project.",
        language: "en",
        n: 2,
      }),
    });
    if (!r.ok) throw new Error(`Voice design failed: ${r.status} ${(await r.text()).slice(0, 120)}`);
    const out = (await r.json()) as { audio_base64: string }[] | { candidates: { audio_base64: string }[] };
    const candidates = Array.isArray(out) ? out : out.candidates;
    return { instruction, candidates };
  });
```

CLIENT: a one-line "describe the voice" box. Show the AI-written `instruction`
so the user sees the casting choice, then render one play button per candidate
(`data:audio/mpeg;base64,${c.audio_base64}`) and let them pick a favourite.

STRETCH (only if the build still fits in one pass): clone a real voice instead.
`POST https://api.fish.audio/model` with `multipart/form-data`
(`title`, `type=tts`, `voices` = a 10-30s reference clip) returns a model id;
pass it to `/v1/tts` as `reference_id` to speak anything in that voice.

TRANSLATION — skip:
This kernel is non-linguistic (audio in, or voice timbre out), so do not add a
language selector or a translation pass. Keep the brain-to-voice path direct.

USER FLOW (the entire app — nothing else exists)
1. Land on the page; the headline previews what the demo does for stylist roleplay training.
2. The primary action (a description box that auditions several generated voices, then speaks the app's content in the one the user picks) is one tap away; the rest of the layout supports it.
3. Lovable AI does the thinking, Fish Audio 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. `FISH_AUDIO_API_KEY` (the voice). Ask Lovable to store it as a project
   secret (Project Settings -> Secrets); grab the key from
   https://fish.audio/go-api. Read it only on the server and send it as
   `Authorization: Bearer ${process.env.FISH_AUDIO_API_KEY}`. Never prefix with
   `VITE_`, never call api.fish.audio from the browser.

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.