kentjuno/omnivoice_playground

★ 15TypeScriptAudience · vibe coderComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((repo))
    Voice Input
      Text description
      Audio clip upload
      Voice cloning
    Interface
      Studio Noir theme
      Timeline editor
      Drag and drop tracks
    Tech
      React frontend
      TypeScript UI
      Python backend
    AI Engine
      OmniVoice model
      GPU acceleration
      CPU fallback
    Developer Tools
      Mock Mode
      No model needed
      Quick UI testing
    Setup
      run.bat launcher
      Linux macOS script
      Auto install deps

mindmap root((repo)) Voice Input Text description Audio clip upload Voice cloning Interface Studio Noir theme Timeline editor Drag and drop tracks Tech React frontend TypeScript UI Python backend AI Engine OmniVoice model GPU acceleration CPU fallback Developer Tools Mock Mode No model needed Quick UI testing Setup run.bat launcher Linux macOS script Auto install deps

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Generate realistic spoken audio from a text description of a voice style, like 'young female, excited tone'.

USE CASE 2

Clone a voice by uploading a short audio clip and producing new speech that matches it.

USE CASE 3

Arrange and edit AI-generated audio clips on a visual timeline, like a lightweight audio workstation.

USE CASE 4

Test and explore the studio UI instantly using Mock Mode, with no large model download required.

Tech stack

TypeScriptReactPythonOmniVoiceNVIDIA CUDANode.js

Getting it running

Difficulty · moderate Time to first run · 30min

Windows: double-click run.bat, it handles Python check, virtualenv, deps, and opens the browser. Linux/macOS have an equivalent script. GPU (NVIDIA) speeds up generation, CPU fallback works but is slower. Mock Mode skips model download for instant UI testing.

No license is mentioned in the explanation.

In plain English

Studio Noir - OmniVoice Playground is a web interface for experimenting with AI-generated speech. It is built on top of a text-to-speech model called OmniVoice and lets you produce spoken audio from text in two different ways: by describing the voice you want in plain English (for example, "female, young adult, high pitch, excited"), or by uploading a short audio clip of someone speaking so the system can copy that voice's characteristics. The interface is designed to look like a professional audio workstation. It shows a timeline with waveform grids where you can arrange and edit audio clips, adjust playback speed, and manage tracks with a drag-and-drop layout. The visual style is dark and cinematic, which the author calls Studio Noir. The front end is built with React and TypeScript, while a Python server running in the background handles the actual speech generation. Speech synthesis runs significantly faster if your computer has an NVIDIA graphics card, because the underlying model uses the GPU for computation. The README includes troubleshooting steps for getting the correct software versions installed when GPU acceleration is not activating properly. If you have no compatible GPU, the tool falls back to running on the CPU, which is slower but still functional. For people who just want to explore the interface without downloading the AI model, there is a Mock Mode. In this mode the application runs immediately with no model download required, so developers can test the visual layout and controls without waiting for a large file. Setup on Windows is handled by a launcher script called run.bat. Double-clicking it checks for the right Python version, creates an isolated environment, installs all dependencies including the GPU-optimized packages if applicable, compiles the frontend, and opens the app in a browser automatically. A similar script is available for Linux and macOS.

Copy-paste prompts

Prompt 1

I'm using the OmniVoice Playground repo. How do I describe a voice in text to generate speech, what format or keywords does the voice description expect?

Prompt 2

I'm setting up kentjuno/omnivoice_playground on Windows. The run.bat script finished but GPU acceleration isn't activating. What should I check first?

Prompt 3

I want to clone a voice using omnivoice_playground. Walk me through how to record or prepare a short audio clip that will give the best cloning results.

Prompt 4

I'm a developer exploring kentjuno/omnivoice_playground. How do I enable Mock Mode so I can test the UI without downloading the OmniVoice model?

Prompt 5

I have omnivoice_playground running. How do I arrange multiple AI-generated clips on the timeline and export the final mixed audio?

Open on GitHub → Explain another repo

← kentjuno on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.