Built in Hong Kong

The AI workspace built for Hong Kong.

Weather, transit, Gmail, slides and storyboards — in Cantonese, out of the box. Every app on one sign-in: Studio for multimodal chat and live voice, Transcribe for audio, Notebook for research, Storyboard for shots, Mindmap for ideas, and Slides for decks — all models, one credit pool.

Enter Studio Explore apps

Starter credits on sign-up. No card required.

190+
Models
9
Apps
1Mtokens
Context
150+
Voices
Apps

Nine apps. One sign-in.

One Google account, one credits pool — every app shares them. Start anywhere, switch without re-signing in.

Drag to explore
01 Flagship

AI Studio

The flagship workspace. Multimodal chat across 160+ models, live voice, multi-agent collaboration, deep research, image, video and music synthesis, a code workspace and persistent memory.

Learn more
02

Transcribe AI

AI audio and video transcription from uploads or a YouTube URL, with speaker diarization, multi-provider routing, and export to text, SRT and VTT.

Learn more
03

Notebook

Source-grounded AI workspace. Upload documents, ask grounded questions, and generate briefs and notes with traceable citations.

Learn more
04

Mindmap

Generate mindmaps from any topic and turn them into presentations. Edit nodes, restructure branches, and present straight from the browser.

Learn more
05

AI Slides

Generate polished presentations from a single prompt. Pick a model, edit slide-by-slide, and export when ready.

Learn more
06

Storyboard

Break a script into shots, generate first/last/reference stills, then render each clip.

Learn more
07

Drink Record

Log every drink, track spending and sugar over time, and get AI recommendations based on what you actually order.

Open
08

SmartSpend

Track expenses, categorise spending automatically, and forecast next month with AI. Multi-currency and receipt capture.

Open
09

Score

Write, edit and play back music notation in the browser. Transcribe from a photo or audio, or compose from a prompt.

Open
Why here

Most AI is built for somewhere else.

Ask in Chinese and get spoken Cantonese back — 嘅, 咗, 喺, 嚟 — not textbook Mandarin. With Hong Kong's own data wired in.

It answers in Cantonese

Write in Chinese and Studio replies in spoken Cantonese, not Mandarin prose. No prompt engineering, no language switch, no reminding it every turn.

Hong Kong data, built in

Live HKO weather and warnings, MTR and bus arrivals, Transport Department traffic, and HK plus US market quotes — read from the source, not guessed.

Every model, one balance

Gemini, GPT, Claude, Grok, Qwen, GLM, MiniMax, DeepSeek and Kimi on a single prompt surface. Top up once and spend it across every app.

Capabilities

HK-native tools. Global model reach.

Real-time weather, MTR, bus, and Gmail — Cantonese by default. Then slide decks, storyboards, research and code on top.

01

Cantonese-first AI Chat

Responds in spoken Cantonese when you write in Chinese — no language-switch needed.

02

Multi-agent collaboration

Planner, researcher, critic — orchestrated in parallel or sequence on a single task.

03

Deep Research

Multi-step retrieval across the live web. Synthesised answers with traceable citations.

04

Image & Video synthesis

Nano Banana Pro stills, Seedream 5.0, Gemini Omni cinematic motion, Seedance 2.5, Wan 3.0 and MiniMax H3 — up to 4K.

05

Voice & Music

Live voice across Gemini Live, GPT Realtime, Grok Voice and Qwen Audio Realtime, 150+ named TTS voices.

06

Document Intelligence

Reason across millions of tokens. Context caching keeps your reference corpus warm between sessions.

07

Persistent Memory

Auto-captured facts and preferences, recalled across every chat. Inspect, edit, delete or pause it anytime.

08

HK & Connectors

Live HKO weather, TD traffic, MTR/bus schedules, and market quotes built in, plus OAuth bridges to Drive, Gmail, Notion, Outlook and GitHub.

09

Study Companion

Auto-generated quizzes and flashcards from any thread or file, with TTS narration in your chosen voice.

Model Roster

170+ models. One prompt surface.

Auto-router picks the best model for the job — or pin a specific one. Routing is reversible per turn.

Text & Reasoning
  • Gemini 3.8 Flashfrontier
  • GPT 6 Astraflagship
  • Claude Opus 5coding
  • Claude Fable 5writing
  • Grok 4.6STEM
  • Qwen 3.8 Maxvision
  • GLM-5.3Zhipu
  • DeepSeek V4 Pro384K out
  • Kimi K2.5open
Image
  • Nano Banana Proquality
  • Nano Banana 24K
  • GPT Image 2 Promasking
  • Grok Imagine Image 2.0I2I
  • Seedream 5.0 ProBytePlus
  • Qwen Image 3.0 Pro3 refs
  • MiniMax Image 0121:9
Video
  • Gemini Omni 1.1 Flasheditable
  • Gemini Omni Flashpreview
  • Seedance 2.5BytePlus
  • Wan 3.0 VideoQwen
  • MiniMax H32K
  • Grok Imagine Video 1.5I2V
Voice & Research
  • Lyria 3.5music
  • MiniMax Music 3.0vocals
  • Gemini 3.1 Flash Livelive
  • GPT Realtime 2.1live
  • MiniMax Speech 2.8 HDTTS
  • Fish Audio S2.1-ProTTS
  • Qwen Audio Realtime Pluslive
  • Deep Research Maxagent

Voices · Zephyr · Puck · Charon · Kore · Aoede · Fenrir · Leda · Orus · Callirrhoe · +150 more

Getting started

Three steps. One credit balance.

No per-app setup. Sign in once and every module above is ready to use.

  1. Sign in once

    Use Google, Microsoft, GitHub, or a verified email or phone number. One account signs you into every app on this page.

  2. Open an app, pick a model

    Launch Studio, Transcribe, or any module above. Inside Studio, choose a model from the picker, or leave it on auto-router.

  3. Spend from one balance

    Every chat reply, transcription, or render draws from the same credit balance. Top up once in Billing, use it in any app.

Trust

Data handling, without the fine print.

We treat your data the way we'd want our own treated. Three things you should know:

Full terms & policy

What we collect

Only your Google profile — name, email, avatar — to verify identity and personalise your space.

How it's stored

History, files and generated media live in encrypted Google cloud storage, scoped to your account, synced across devices.

We don't sell it

Never. No third-party brokerage, no ad-targeting, no training on your private data.

FAQ

Questions, answered.

What is Alchemys App?

Alchemys App (shown as SPCY on spcy.hk) is a Hong Kong–built workspace of AI apps that share one sign-in and one credits balance: Studio, Transcribe, Notebook, Storyboard, Mindmap and Slides.

Do I need a separate account for each app?

No. One account (Google, Microsoft, GitHub, or a verified email/phone) signs you into every app. Credits are shared across the whole workspace, so you can start in Studio and continue in Transcribe or Slides without signing in again.

Which AI models can I use?

More than 160 models across Gemini, GPT (including GPT 6 Astra), Claude, Grok, Qwen, GLM, MiniMax, DeepSeek, Kimi, Doubao Assistant and others. Per-model credit costs are listed on the public pricing page.

How does pricing work?

New accounts receive starter credits. Usage is billed in credits per model. See the pricing page for current per-model costs. Managing a balance requires sign-in.

Can I use it in Cantonese?

Yes. The interface supports English, Cantonese (廣東話) and Simplified Chinese. Transcribe AI is built for Cantonese, English and Mandarin speech, including speaker diarization.

Where is my data stored?

Account identity comes from Google (name, email, avatar). History, files and generated media live in encrypted cloud storage scoped to your account. Alchemys does not sell your data or train on your private content.

Start with one prompt.

Sign in with Google, Microsoft, GitHub, or a verified email or phone. Starter credits are on the house.

Enter Studio Model pricing