Docs
Account & Settings
Registration, login, and configuring your account.
Registration
Screenshot: Registration page
To get started with Audiobook Studio, you'll need to create an account.
1
Create your account
Visit the registration page and sign up with your email and a password.
2
Wait for approval
After registering, your account will be in a pending state. An administrator will review and approve your account. You'll see a "pending approval" message if you try to log in before being approved.
3
Start using the app
Once approved, your account becomes active and you can log in and start creating audiobook projects.
Some instances may have open registration enabled, in which case your account is activated immediately — no approval wait needed.
Logging In
Screenshot: Login page
Log in with the email and password you used during registration.
Account Statuses
Your account can be in one of three states:
- Active — Full access to the application. You can create projects, generate audio, and export.
- Pending — Your registration is awaiting approval. You'll see a waiting screen when you try to log in.
- Paused — Your account has been temporarily suspended. Contact your administrator if you believe this is an error.
Settings
Screenshot: Settings dialog showing API key fields
Open the Settings dialog (⚙) from the top bar to configure your account:
API Keys
- TTS provider & API key — Required for text-to-speech generation. Choose from ElevenLabs, OpenAI TTS, or Google Cloud TTS. See the TTS Provider Setup page for step-by-step instructions.
- LLM provider & API key — Choose your preferred AI provider (OpenAI, Anthropic, Google, etc.) and enter its API key. Used for intelligent character detection.
Your API keys are personal to your account — they are never shared with other users. Each user brings their own keys and pays their provider directly.
Generation Settings
- Parallel generation — How many audio snippets to generate simultaneously (default: 2). Higher values are faster but use more API quota.