Studio

One chat box, every model that matters

Ask a question, upload a file, generate an image or video, or talk to it out loud. Studio routes what you type to the right model and the right tool, so you never have to know which one to pick.

Sign in to start — every new account gets a free credit balance shared across all Alchemys apps.

What's newUpdated October 2026

Recently added to Studio

Six things Studio does now that it could not a month ago.

New

A photoreal face for Live voice

Live voice can show a photoreal avatar in 2D or 3D, animated from a real photograph. Use a bundled portrait, or upload your own photo and it rigs itself the same way.

New

Code that actually runs

Ask for a calculation or a quick script and Studio runs the JavaScript it wrote inside an isolated sandbox — no network, no files, capped memory and time — then shows you the output.

New

Gap-free read-aloud

Auto read-aloud with MiniMax voices now streams the whole reply over one continuous voice session, so sentences flow into each other instead of pausing between them.

New

Canva, OneDrive and a smarter Calendar

Find, create, export and autofill Canva designs, read files from OneDrive, and let Calendar see shared and secondary calendars — not just your primary one.

New

Thinking effort, chosen for you

On Auto, Studio now picks how hard to think on each turn together with the model. Set a level yourself and it is always respected.

New

Log a drink or an expense from chat

Tell Studio — typed or in Live voice — what you bought, and it prepares an editable card for Drink Record or SmartSpend. Nothing is saved until you confirm, and never twice.

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, Slack and more once you connect them, and chat with Studio from Telegram.

Getting started

About five minutes to your first useful answer.

  1. 1

    Sign in

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

  2. 2

    Start a new chat

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

  3. 3

    Pick a model, or don't

    The model picker sits at the bottom-right of the composer. Choose “Auto” at the top of its list and the best model for your question is picked for you — the button then reads “Auto-select”.

  4. 4

    Type, talk, or attach a file

    Type your message, then send it with Ctrl+Enter (⌘+Enter on a Mac) on a computer, or Enter on a phone — you can change this under Send Shortcut in the Settings panel. Tap the microphone to dictate instead, or use the “+” button to attach a file or a YouTube link.

  5. 5

    Read, switch, and carry on

    The answer streams in as it's written. Under it you get Copy, Regenerate and More options (Read aloud, Rewrite, Fork from here), and you can Edit your own message. Not happy with it? Switch models mid-chat — everything so far carries over — or use Model Arena to send the same question to a few models side by side and continue with whichever answered best.

Where things are

Every part of Studio, and what lives there.

Pages

  • Files — File Archives: everything you uploaded or Studio generated. Filter by Source, Status (Active or Expired) and Type, or search by filename.
  • Code — Code Workspace: code projects with an editor and a preview, a Run button for Python, and export as .zip.
  • Live Chat — Real-time voice, translation and music — see Voice.
  • Connections — Connect services, add webhooks and MCP servers, link Telegram and manage your sign-in methods.
  • Personalization — Memory, custom system instruction, response language, knowledge base, skills, custom voices, reminders and routines, Zero Data Retention and Delete data.
  • Settings panel — The sliders button in the header (or Model Settings in the settings menu): Select Model, image and video options, Google tools for Gemini models, system instruction, Send Shortcut, TTS voice output, storage use, Install App and Force Refresh.
  • Settings menu — The gear at the bottom of the sidebar: Personalization, User Memory, theme, interface language, Model Settings, Response Language, Upload to, Raw Mode, Refine Media Prompts, Research Mode, Auto-read responses, Usage Limit and Help Center.

What the settings do

  • Response Language — Default (follow interface language), Cantonese only, Mandarin only, English only, or Unspecified.
  • Upload to — GCS Cloud (Google Cloud Storage) or Google Drive. Uploads to Drive are limited to 44 MB.
  • Raw Mode — Turns off all preserved system instructions (agentic context).
  • Refine Media Prompts — Lets the AI rewrite your prompt before image or video generation. When off, your original prompt is sent unchanged.
  • Research Mode — Deeper, slower web search for non-Gemini models: more results per query, more full pages fetched and a bigger tool-loop budget.
  • Auto-read responses — Automatically generates speech audio after each model reply finishes.
  • Thinking Mode — For models that support it, choose how hard to think, from Auto (default) to Max.
  • Send Shortcut — Which key sends your message: Enter, Ctrl+Enter, Tab+Enter or Alt+Enter.

Models & modes

The picker next to the composer lists the main models. The full list, grouped by provider and by what each one is for, is under Select Model in Settings.

Five ways of working

Auto-select

Reads your question and picks the model for you — the safe default.

Multi-agent

A planner splits the job into up to 12 steps, helpers work through them four at a time, and everything is merged into one answer. Find it under “Others” in the picker.

Model Arena

Sends the same question to two or three models at once so you can compare answers and continue with the one you prefer. Find it under “Others”.

Free

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

Open

An open model for everyday questions, without the premium tier. Find it under “Others”.

Providers

The picker next to the composer shows the main families — Gemini, Dola, Doubao Assistant, GPT, Claude, Kimi, Grok, MiniMax, DeepSeek, MiMo and Hunyuan. Open Select Model in Settings for the full list, including Qwen, GLM, Mistral, Perplexity and more: filter by provider or type (text, image, video, music, TTS, agent), search by name, and sort by capability 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 “+” button next to the composer. Local File adds a document, image, video or audio clip from your device (you can also drag a file into the window). Uploaded Files reuses something you already uploaded, and YouTube Link adds a video by its address. On a phone the menu also offers Take Photo, Record Video and Album. To keep a file's content in memory, open User Memory and choose Attach file.

Web, maps & links

Studio can look things up on the web. Use the Search skill for a question, or switch on Google Search, Google Maps and URL Context in the Settings panel — those three work with Gemini models only. Other models search the web and read links with built-in tools. Research Mode in the settings menu makes that search deeper but slower.

Memory & skills

Teach it once instead of repeating yourself every session.

What it remembers

Studio can save notes about your background and preferences and bring the relevant ones back in later chats. Switch this on or off with “Allow model to remember”. Read, add, edit or delete memories in User Memory (settings menu) or on the Personalization page. “Access chat history” lets the model see earlier turns and search your other chats when a question needs them.

Skills & your own documents

A skill is a saved way of working that you attach to one message. Pick one from the Skills button next to the composer, type “/”, or use the gallery on the Personalization page (Mine, Built-in, Templates), where you can also create your own or have AI generate one. Upload documents to your Knowledge Base and Studio can search them when a question fits — switch that on with “Auto-search knowledge base”.

Add-on tools

Connect outside tool servers — the Model Context Protocol standard — under MCP Servers on the Connections page, so Studio can reach your own systems.

Voice

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

Read aloud & dictation

Every reply has Read aloud under its More options menu. In the Settings panel, switch on TTS Voice Output and choose a read-aloud model — Fish Audio, Gemini, MiniMax, OpenAI, Qwen or xAI voices — or turn on Auto-read responses in the settings menu so new replies play themselves. You can also create your own voice on the Personalization page for Fish Audio and MiniMax. Tap the microphone next to the composer to dictate instead of typing.

Live voice

Open Live Chat from the sidebar for a real-time voice chat you can interrupt. Turn on Camera or Share Screen and it sees what you see, and choose a 2D or 3D Face. Switch Mode to Translation to speak and hear your words translated aloud, or to Music to steer a real-time music session with weighted prompts. Save the session as a chat when you finish. Live uses credits while it runs, at a per-minute rate, and the session closes if your credits run out.

Automation

Set it up once and let it run without you.

Scheduled routines

On the Personalization page, open Reminders & Routines → Routines and add a routine: a prompt that runs on a schedule. Choose where results go — in-app as a chat, Telegram once you've linked it, or a webhook event (routine.completed). After three failures in a row a routine switches itself off.

Reminders

Under Reminders & Routines → Reminders you can add reminders, sort them into folders and show completed ones. Set Quiet hours (From and Until) so reminders stay silent, or open the Reminders app for the full view.

Webhooks

On the Connections page, open Outbound Webhooks, add your URL and choose an event: Chat created, Chat message, Expense created, Expense updated, Transcription completed, Score saved, Slides generated or Notebook created. Add a secret if you want the calls to be signed, and use Test to send a sample.

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. Choose Attach Notebook in the “+” menu to cite a Notebook's sources in a chat and pull its outputs back in as attachments.

Managing chats

Open a chat's menu to Pin, Rename, Move to folder, Duplicate, Regenerate Title, Share or Delete it. On any reply, More options → Fork from here starts a new chat from that point and leaves the original alone. Share link makes a read-only link that expires after seven days and can be revoked sooner; you can also copy the chat as text or export it as Markdown, JSON or PDF. Temporary Chat in the sidebar saves nothing at all.

Connected apps

Connect a service on the Connections page and Studio can use it in chat. Type “@” in the composer to attach a record from another Alchemys app, or to point at a connected service. To chat from your phone, link Telegram on the same page with a link code — Telegram chats show up in your history but stay read-only in Studio, so you continue them in Telegram.

What each connection can do

  • Gmail and Outlook Mail — search and read mail, and write drafts. Studio never sends an email for you.
  • Google Calendar and Outlook Calendar — list your calendars, read events and add events.
  • Google Drive and OneDrive — list and read files.
  • Google Docs & Sheets — create and edit documents and spreadsheets.
  • Notion — search your workspace.
  • GitHub — search repositories, read files and issues, and open an issue.
  • Slack — list channels, read messages and post a message.
  • Linear and Asana — look up issues, projects and tasks, and create new ones.
  • Canva — find, create, export and autofill designs, and upload images.
  • Meta — work with Facebook Pages and Instagram posts and comments; publishing asks you to confirm first.

Good to know

The specifics, in one place.

  • Supported filesPDF, text, Word, Excel, PowerPoint, images, video and audio — up to 240 MB each (44 MB when Upload to is Google Drive)
  • Sharing a chatRead-only link, expires after 7 days
  • Where files liveFile Archives (Files in the sidebar). Chat uploads expire after 7 days unless already read into text; generated files, knowledge-base documents and Drive files don't
  • Free allowancePer model: hourly quota refills gradually from your last use in the past 12 hours; daily limits reset at midnight
  • CreditsTop up by card on billing; every model's price is on the pricing page
  • Zero Data RetentionOptional, on the Personalization page: Off, Preferred or ZDR only — limits Studio to providers we classify as not training on your inputs (about training, not deletion)
  • Your limitsSettings menu → Usage Limit: your credits, your tier's limits per model group, and when they refill
  • Deleting your dataPersonalization → Delete data: pick Chat history, Memory and/or Settings, then Delete selected. It can't be undone

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?
We do not train models on your content. The AI providers that process your requests follow their own terms, and some free-tier models may use inputs to improve their products. On the Personalization page, set Zero Data Retention to “ZDR only” to restrict Studio to providers we classify as contractually not training on your inputs, or to “Preferred” to use one whenever a provider serves the model. Despite the name it is about training, not deletion — it does not shorten how long a provider keeps data or limit where it is processed, and our own logs still apply. 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 (Install App in the Settings panel), or link Telegram on the Connections page to chat with Studio from your phone. Telegram chats show up in your history but stay read-only in Studio.
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.
Why doesn't Enter send my message?
On a computer the default send key is Ctrl+Enter (⌘+Enter on a Mac), so Enter just adds a new line. Change it under Send Shortcut in the Settings panel — Enter, Ctrl+Enter, Tab+Enter or Alt+Enter. On a screen narrower than 1000 px, such as a phone, Enter always sends.
Can I chat without saving anything?
Yes — choose Temporary Chat in the sidebar. Messages sent in a temporary chat won't appear in your history and won't be saved.
Can Studio send emails for me?
No. With Gmail or Outlook connected it can search and read mail and write a draft in your mailbox, but you send it yourself.

Start your first chat

Sign in, ask it anything, and see which model answers best.