Getting Started with Verbatik

This guide walks you through creating your account, setting up your workspace, and making your first API call.

Creating Your Account

Sign Up

1. Navigate to the Verbatik sign-up page.
2. Create an account using:
   • Google — One-click registration with your Google account.
   • Email & Password — Enter your name, email, and a secure password.
3. After signing up, you'll receive a verification email. Click the link to verify your address. Verification links expire after 24 hours.

Email Verification

• A verification email is sent automatically when you register with email/password.
• If you change your email later, a new verification email is sent to the new address.
• Expired tokens can be re-requested from your profile settings.

Onboarding

When you sign in for the first time, you'll be guided through a short onboarding flow:

Step 1: Profile Setup

Enter your display name and optionally upload a profile picture. This is visible to your workspace members.

Step 2: Create a Workspace

Every account needs at least one workspace. A workspace is the central hub for your team's voices, API keys, billing, and usage. Enter a name — a URL-friendly slug is generated automatically.

Step 3: Invite Collaborators (Optional)

Invite team members by email. This step can be done later from workspace settings.

Step 4: Done

You'll be redirected to your workspace dashboard where you can start exploring voices, generating speech, and managing API keys.

Your First API Call

Once your workspace is set up:

1. Go to API Keys in your workspace sidebar.
2. Click Create API Key and give it a name.
3. Copy the key — it is only shown once.
4. Make your first TTS request:

curl -X POST https://api.verbatik.com/api/v1/tts \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: text/plain" \
  -H "X-Voice-ID: jenny-en-us" \
  --data "Hello, welcome to Verbatik!" \
  --output hello.mp3

Next Steps

• Billing & Payments — Understand the prepaid balance model and top-ups.
• Text-to-Speech — Full reference for the TTS endpoint.
• Voice Library — Browse 2,700+ pre-trained voices.
• Voice Cloning — Clone a voice from an audio sample.
• Voice Design — Create a voice from a text description.
• Text-to-Music — Generate AI music from prompts and lyrics.
• MCP Integration — Connect Verbatik to AI assistants via Model Context Protocol.