How can we help?
Table of Contents
< All Topics

AI Generator: SFX and Text to Speech

The AI Generator is a powerful tool designed to generate audio content, including sound effects (SFX) and speech, using advanced AI models. Below is a detailed guide to its features and functionality.

You can show the AI Generator panel via the ‘View’ menu

Main Features

 

1. Generation Type Selection

  • SFX (Sound Effects): Generate sound effects based on your input text and settings.
  • Speech: Generate speech using a selected voice model.

2. GeneratION Options

  • Add to Taglist: Send the files to the selected Taglist for quick previewing.  If this is OFF then the output folder is opened in Explorer/Finder at the end of Generation. 
  • Use Custom Path: Allows you to specify a custom output folder for generated files. It not set then files will go the the globally set Transfer Path
  • Share to Community Library: (SFX Only) – Uploads a copy to our server to possible inclusion in a future FREE basehead community library.  Please leave this ON as we do a lot for you and this doesn’t cost you anything extra beside a few seconds of upload time and you will be giving back to the entire community.

3. API Key Management

  • API Key Input: Enter your ElevenLabs API key to enable the generator.
  • Get API Key Button: If you don’t already have an API key then click this obtain a FREE API key using our affiliate link to help support us.
  • Subscription Info Button: Displays detailed information about your ElevenLabs subscription, including tier, usage, and available features.

4. SFX Settings

  • Duration: Adjust the duration of generated sound effects (0.1 to 22 seconds).
  • Seed Value: Set a seed for consistent results or leave it at 0 for random generation.
  • Prompt Influence: Control how closely the generated sound follows your input text.
  • Variations: Specify the number of variations to generate for each prompt.

5. Speech Settings

  • Voice Selection: Choose from a list of available voices retrieved from the ElevenLabs API.
  • Voice Stability: Adjust the stability of the generated voice (higher values produce more consistent results).
  • Voice Similarity: Control how closely the generated voice matches the original voice character.
  • Voice Expression: Adjust the expressiveness and emotion of the generated speech.
  • Speaker Boost: Enable or disable speaker boost for enhanced audio output.
  • Model Selection: Choose from different AI models for speech generation.

This Feature is Available in all ‘Premium’ Editions of basehead.