# Dia

> A 1.6B text-to-speech model for realistic multi-speaker dialogue

- Category: Multimodal Generation / Audio, Music & Voice
- Language: Python
- Licence: Apache-2.0
- Repository: https://github.com/nari-labs/dia
- Canonical page: https://ai-tldr.dev/tools/dia/

## In short

Dia is a 1.6B-parameter text-to-speech model from Nari Labs that turns a written transcript directly into spoken dialogue. You write lines tagged with [S1] and [S2], and the model generates audio for a back-and-forth conversation between two speakers. It sits in the Audio, Music & Voice category of the Multimodal Generation tools and is open-source, written in Python and licensed Apache-2.0.

## Overview

Dia is a 1.6B-parameter text-to-speech model from Nari Labs that turns a written transcript directly into spoken dialogue. You write lines tagged with [S1] and [S2], and the model generates audio for a back-and-forth conversation between two speakers.

It is aimed at developers and researchers who need conversational speech rather than a single narrator. Beyond plain words, Dia can produce nonverbal sounds such as laughter, coughing, and throat-clearing using inline tags, and you can condition the output on a short audio prompt to control voice, emotion, and tone.

Within the speech and audio space, Dia is an open-weights alternative to hosted dialogue TTS services. The weights are on Hugging Face under Apache-2.0, and you can run it through the project's own code, a Gradio UI, a CLI, or the Hugging Face Transformers integration. The model currently supports English only.

## What it does

- Generates two-speaker dialogue from a transcript using [S1] and [S2] tags
- Produces nonverbal sounds such as (laughs), (coughs), (sighs), and (clears throat)
- Voice cloning by conditioning on a short 5-10 second audio prompt with its transcript
- Open weights on Hugging Face (Dia-1.6B-0626) under the Apache-2.0 license
- Runs via the project repo, a Gradio web UI, a CLI, or Hugging Face Transformers
- Sampling controls including guidance_scale, temperature, top_p, and top_k for output tuning

## Getting started

You can run Dia through Hugging Face Transformers or from the project repo. The Transformers path needs the main branch of transformers and a CUDA GPU.

1. Install via Transformers

   Install the main branch of transformers, which contains the Dia implementation.

```bash
pip install git+https://github.com/huggingface/transformers.git
```

2. Generate dialogue audio

   Load the processor and model, pass a transcript using [S1] and [S2] tags, then save the result. Requires a CUDA device.

```python
from transformers import AutoProcessor, DiaForConditionalGeneration

torch_device = "cuda"
model_checkpoint = "nari-labs/Dia-1.6B-0626"

text = [
    "[S1] Dia is an open weights text to dialogue model. [S2] You get full control over scripts and voices. [S1] Wow. Amazing. (laughs) [S2] Try it now on Git hub or Hugging Face."
]
processor = AutoProcessor.from_pretrained(model_checkpoint)
inputs = processor(text=text, padding=True, return_tensors="pt").to(torch_device)

model = DiaForConditionalGeneration.from_pretrained(model_checkpoint).to(torch_device)
outputs = model.generate(
    **inputs, max_new_tokens=3072, guidance_scale=3.0, temperature=1.8, top_p=0.90, top_k=45
)

outputs = processor.batch_decode(outputs)
processor.save_audio(outputs, "example.mp3")
```

3. Or install from the repo

   Clone the repository and install in editable mode, then run a bundled example. A Gradio UI (app.py) and CLI (cli.py) are also included.

```bash
git clone https://github.com/nari-labs/dia.git
cd dia
pip install -e .
python example/simple.py
```

## When to use it

- Generating two-speaker dialogue for podcasts, demos, or scripted conversations
- Adding nonverbal cues like laughter or sighs to make synthetic speech sound more natural
- Cloning a target voice from a short reference clip to keep a consistent speaker
- Researching or prototyping open-weights conversational TTS without a hosted API