Skip to content

How Studio works

Studio is the chat-based builder where you create, test, and publish voice agents. This is what every panel does and the typical flow from idea to live call.

1. Start an agent

From the welcome screen you have three paths:

  • Describe what you want in plain English and let AI draft the config.
  • Pick a template (sales, support, booking, etc.) as a starting point.
  • Import a saved JSON config if you're cloning a previous agent.

First-time users go through a short onboarding that asks for role, tone, and an opening line.

2. Three panels: chat, config, top bar

Inside an agent you see:

  • Chat on the left — your conversation with the AI builder.
  • Config editor on the right — a live, scrollable view of every field on the agent (name, role, language, voice, model, advanced settings).
  • Top bar — agent name, Test and Publish buttons, status pill (dirty / saving / saved), billing tier, attached phone number.

Edits in either panel reflect in the other immediately.

3. Build by talking to the AI

Tell the AI what you want — "make the greeting friendlier", "add a step to confirm the email" — and it proposes a change card you can approve or reject. Approved changes apply to the draft instantly.

The AI also asks inline setup questions when something important is missing.

4. Setup questions block publish

Critical fields (role, success criteria, opening line) appear as setup cards. You must answer or skip them before publishing. Each card has a "draft this for me" shortcut if you want AI to fill it in.

5. Test in the browser before going live

Click Test to call the agent from your laptop mic. You hear the opening line, the agent transcribes you in real time, and the transcript shows below.

Browser test calls:

  • Are capped at two minutes
  • Don't need a phone number attached
  • Are free — they don't bill against your credits

6. Publish, then attach a number

Publishing pushes the draft to production. If anything is missing, the publish modal shows blockers and lets you fix them inline.

Published agents still need a phone number attached under Numbers before real calls route to them. See the Telephony guide for the BYOC flow.

7. Drafts vs. live: no rollback

Changes after publish create a new draft. Hitting Publish again overwrites the live config — there is no version history. If you need a backup, clone the agent from the agent list before making big changes.

8. Slash commands and JSON edit

In chat, try:

CommandWhat it does
/voiceShow and change the voice
/modelPick a different LLM
/test-callOpen the test panel
/publishTrigger the publish flow
/helpList all available shortcuts

The top bar also has a JSON editor — paste a saved config or export the current one for sharing or backup.

What's next