Skip to main content
Invook supports high-quality text-to-speech (TTS) models to bring your scripts and text content to life. Each model uses a specific number of credits per 1,000 characters.
Credits are deducted from your account balance based on character count. Free plan users receive 150 credits/month. See FAQs for more details.

​
Available Audio Models

Model NameCredits per 1,000 Characters
ElevenLabs TTS (V3)10 credits

​
How to Use Audio Models

  1. Add an Audio Model Block to your Canvas using the Add Block tool.
  2. Connect a Prompt Block or Text Block containing the script you want to convert.
  3. Run the model to generate the audio file.
  4. Listen to or download the result from the Audio block.
New to the Canvas? Follow the Create Your First Asset guide for a full walkthrough.

Image Models

Browse image generation models.

Video Models

Browse video generation models.

Text Models

Browse text generation models.