GraphCanon updated 3w · GitHub synced 3w · 28 views this month
Decision brief
Dia is an open-weight text-to-dialogue model providing full control over scripts and voices, ideal for generating ultra-realistic dialogue.
Good fit when
- When you require precise control over voice and script in the creation of highly realistic dialogues
- If your project involves GPU acceleration and you prefer working with CUDA-supported platforms like Pytorch 2.0+
Avoid when
- If your setup lacks a GPU, as Dia has not yet added CPU support
- In scenarios where immediate real-time performance is critical since the first run could be longer due to additional codec downloads
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (251d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install diaSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Dia is an open-weight text-to-dialogue model that allows full control over scripts and voices.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Jul 29, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 29, 2026)
```python from transformers import AutoProcessor, DiaForConditionalGenerationSource link
Tags
README
or install with uv
uv pip install git+https://github.com/huggingface/transformers.git
Run `hf.py`. The file is as below.
```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")
Install dia
pip install -e .
Or you can install without cloning.
```bash
---
# Install directly from GitHub
pip install git+https://github.com/nari-labs/dia.git
Now, run some examples.
python example/simple.py
Install via uv
You need uv to be installed.
---
## 💻 Hardware and Inference Speed
Dia has been tested on only GPUs (pytorch 2.0+, CUDA 12.6). CPU support is to be added soon.
The initial run will take longer as the Descript Audio Codec also needs to be downloaded.
These are the speed we benchmarked in RTX 4090.
| precision | realtime factor w/ compile | realtime factor w/o compile | VRAM |
|:-:|:-:|:-:|:-:|
| `bfloat16` | x2.1 | x1.5 | ~4.4GB |
| `float16` | x2.2 | x1.3 | ~4.4GB |
| `float32` | x1 | x0.9 | ~7.9GB |
We will be adding a quantized version in the future.
If you don't have hardware available or if you want to play with bigger versions of our models, join the waitlist [here](https://tally.so/r/meokbo).
---
## 🪪 License
This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
For agents
This page has a .md twin and JSON over the API.