FallTalk Audio and Voice Generator

Introduction:

Hello and Welcome to FallTalk, the Open Source Text to Speech (TTS), Voice Cloning, Audio Generation, and Audio Processing Software for Fallout 4. So, why did I create this? Originally, this began as a fun little project to understand how AI works, which could further my career as a software engineer. One day while playing Fallout 4, I encountered a mod with absolutely terrible AI voices. This sparked an idea: what if I combined my project to understand AI and provided the community with a way to create better AI voices?

The main question I've been asked so far is: Why create this when ElevenLabs and xVASynth already exist? I believe the audio quality generated by this tool can be as good as ElevenLabs, and sometimes even better. While it doesn't have the full range of controls like pausing and emotion, since I am not using tortoise tts, selecting a good reference file can give great results. Regarding xVASynth, I think this tool offers a more user-friendly solution for the average person, focusing on convenience.

This new tool will allow you to accurately clone voices from various characters, including the Eyebot, Polymer Labs Announcers, Mr. Gutsy, Liberty Prime, and more. Really, it can accurately clone every voice, from the elevator sounds to the protagonist. These are bold claims, and I have provided audio samples below for your evaluation.

Not only that, it offers an whole host of audio related features for creators to use:

• []LIP and FUZ creation, with any function or bulk method

  []Custom Model Support: Train or download a model and you can use it instantly

  []Bulk RVC: Want to replace the main character? Do it with one simple click, and suddenly Nate now sounds like a super mutant, a synth, or much more. Converts entire folders and optionally creates lips and fuz

  []Bulk Denoiser: Ever hear a mod that has custom audio, but clearly is lower quality and static? The AI denoiser isolates the audio and upscales the voice at the same time.

  []Bulk Upscaler: take low quality sound effects and make them sound high def and crisp

  []Music Generation: Perfect for creating background music or audio jingles. Includes a melody cloning feature using any reference audio. Not trained on any audio... yet. Trained using creative commons sourced training data.

• Sound FX Generation: Create Sound effects on demand, trained using creative commons sourced data.

  This tool does not contain any assets from Fallout 4, but they were used to train the models. The tool will look for your Fallout 4 directory to use reference audio files.

  But Why?

  Well, once the gears go going in my head, I had tons of ideas on how to use the generated but no tool to do it well enough. Here are just a few ideas that got me started: