What you can do

No commands to memorise — say what you want, and Studio picks the tool.

Chat across every major model

Ask questions, get code reviewed, or have something written, then switch between Gemini, GPT, Claude, Grok, DeepSeek, Qwen, MiniMax, GLM and more without starting over.

Generate images, video & music

Describe what you want, get it made, then ask for changes — pictures, short clips with sound, and full songs.

Research it properly

Deep research reads dozens of sources, cross-checks them, and writes a report that links back to every one.

Talk out loud

Open live voice for a real back-and-forth, have it interpret between languages as you speak, or jam on music in real time.

Put a team on it, or compare

Split one job across several helpers working in parallel, or send the same question to a few models and pick the best answer.

Connect your other tools

Reach into Google Drive, Gmail, Notion, GitHub and more once you authorise them, and carry the conversation over to Telegram.

Getting started

About five minutes to your first useful answer.

1

Sign in

Open Studio and sign in — new accounts start with a free credit balance shared across every Alchemys app.
2

Start a new chat

Click “New chat” in the sidebar. The title gets written for you from your first message.
3

Pick a model, or don't

The model picker sits at the bottom-right of the composer. Leave it on “Auto-select” and the best model for your question is chosen for you.
4

Type, talk, or attach a file

Write in the box and press Enter, tap the microphone to dictate instead, or use the “+” button to add a photo, PDF, video or a pasted YouTube link.
5

Read, switch, and carry on

The answer streams in as it's written. Not happy with it? Switch models mid-chat — everything so far carries over — or send the same question to a few models side by side and continue with whichever answered best.

Models & modes

The picker holds every model Studio supports, grouped by provider and by what each one is for.

Four ways of working

Auto-select

Reads your question and routes it to the model best suited for it — the safe default.

Multi-agent

A lead assistant breaks the job into pieces and runs up to eight helpers in parallel, then merges everything into one answer.

Model Arena

Sends the same question to two or three models at once so you can compare answers and continue with the winner.

Free

Always free — hops between free models. Good for quick, everyday questions.

Providers

Below the four modes sit chat, image, video, music and voice models from Google Gemini, OpenAI, Anthropic Claude, xAI Grok, DeepSeek, Qwen, MiniMax, Zhipu GLM, ByteDance Seed and more — filterable by name, ability or price.

Small models are fast and cheap for everyday questions; larger ones earn their keep on reasoning, long writing and code. Some models — and all media generation — spend credits. See pricing, and top up on billing.

Files & the web

Studio isn't limited to what it already knows.

Adding files

Use the “+” next to the composer to hand over a document, photo, video or audio clip — from your device, your camera, your photos, drag-and-drop, or a pasted YouTube link. Tick “remember this” on upload and its content comes back automatically whenever it's relevant, no re-uploading.

Web, maps & links

Turn on web search in settings and Studio looks things up while it answers, marking where each fact came from. Paste a web address and it reads the page before replying; paste a YouTube link and it reads the captions. Ask for directions or opening hours and it checks Google Maps.

Memory & skills

Teach it once instead of repeating yourself every session.

What it remembers

Studio files notes on your background, preferences and the files that matter, then brings the relevant ones back on their own. Anything saved automatically can be read, edited or deleted on the personalization page.

Skills & your own documents

Save a way of working as a skill and attach it for one send — from Tools, by typing “/”, or from the personalization gallery. Upload a set of your own documents and Studio searches yours first, pointing back to the exact file and page it used.

Add-on tools

Connect outside tool services — the Model Context Protocol standard — from personalization settings so Studio can reach your own systems.

Voice

Every answer can be heard, and you can just talk back.

Read aloud & dictation

Every answer has a play button, with voices from Gemini, MiniMax, Fish Audio and Qwen. Turn on read-aloud in settings, choose a voice, and press play — or switch on auto-read so new answers play themselves. Tap the microphone next to the composer to dictate instead of typing.

Live voice

Open live voice for a real-time, interruptible back-and-forth — turn on your camera or share your screen and it sees what you see. A live interpreter mode translates as you speak, and a music-jam mode writes and plays music you can steer while it runs. Talk time is billed by the minute.

Automation

Set it up once and let it run without you.

Scheduled routines

Set a job to run on its own — a daily summary, a weekly report, a regular check on something you care about. Choose where it lands: waiting in the chat, pushed to Telegram, or sent to a URL you nominate. Three failures in a row and a routine switches itself off.

Webhooks

Register a URL of your own on the integrations tab of personalization settings, and Studio notifies it when a chat is created, a reply arrives, a recording finishes transcribing, a deck or notebook is generated, or an expense or score is logged.

Jobs that keep running

Deep research, video and music generation run in the background, tied to your account rather than the device you started them on — start something on your laptop and pick it up on your phone later, with a notice when it's done.

Organize & connect

Keep related work together, and reach into the apps you already use.

Folders & Notebook

Group related chats into a folder and start new chats straight inside one; share a whole folder as a read-only link. Attach a Notebook from the tools menu to cite its sources in a chat and pull its outputs back in as attachments.

Managing chats

Pin, rename, or branch off a chat to try something without touching the original. Share a chat as a read-only link that expires after seven days, export it as text, Markdown, PDF or data, or start a temporary chat that saves nothing at all.

Connected apps

Once you authorise them, Studio can read and write inside Google Drive, Docs, Sheets, Slides, Gmail, Calendar, Outlook, Notion, GitHub and Meta, and carry the conversation over to Telegram. Type “@” in the composer to name the one you mean.

Good to know

The specifics, in one place.

Supported filesPDF, text, images, video and audio — up to 240 MB each
Sharing a chatRead-only link, expires after 7 days
Where files liveYour file archive — browse, preview and download anytime
Free allowanceRolls over a 12-hour window per model; daily limits reset at midnight Hong Kong time
CreditsTop up by card on billing; every model's price is on the pricing page
Zero Data RetentionOptional setting — restrict Studio to providers who never store or train on your inputs

Worth knowing

Don't paste passwords, card numbers or other secrets. Studio gets things wrong sometimes — verify anything that matters, and treat its answers as a starting point, not professional advice. Generated images carry an invisible provenance watermark, and pages simply don't exist for anyone who isn't signed in.

Frequently asked questions

Do I need to know which model to pick?

No — leave it on Auto-select and Studio picks the right model for your question. You can switch mid-conversation or compare a few side by side any time.

What does it cost?

Every new account starts with a free credit balance shared across every Alchemys app. Small models are often covered by a rolling free allowance; larger models and any image, video or music generation spend credits. See the pricing page for the full list.

Is my data used to train anything?

Turn on Zero Data Retention in settings to restrict Studio to providers who guarantee your inputs are never stored or used for training. It's off by default because the strictest setting makes some models unavailable.

Can I use it on my phone?

Yes — install Studio to your home screen for an app-like experience, or link Telegram to carry the same conversation from your phone.

What happens to long jobs if I close the tab?

Deep research, video and music generation keep running in the background. Come back later — even on a different device — and the result is waiting, with a notice that it's done.

One chat box, every model that matters