Plain-AyI
← All projects
Speech & audio

Dia

Turns a written script into realistic spoken dialogue between two voices, including laughs and other sounds.

Research-backed

What it does

Dia is a text-to-speech AI model from Nari Labs. You write a script with two speakers marked, and it produces a natural-sounding conversation in one go.

It can add non-speech sounds such as laughing, coughing or clearing the throat. You can also give it a short audio sample to guide the tone and emotion, or to copy a voice.

It currently supports English only. The model is free to download, and there's an online demo to try it.

Who it's for

Podcasters, game makers, researchers and developers who need realistic AI-generated dialogue.

Can I use it without coding?

With some setup. There's an online demo; running it yourself needs Python and ideally a graphics card. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Web browser
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Try the free online demo on Hugging Face.
  2. To run it yourself you need a computer with a graphics card.
  3. Install Dia, then start its simple web interface.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it