# Dia

> Dia generates two-speaker dialogue (\[S1\]/\[S2\] tags) with non-verbals like laughter, and can clone a voice from a 5-10 second audio prompt. Apache-2.0 code and Apache-2.0 weights on Hugging Face. English only. Tested on GPU only (about 4.4 GB VRAM in bfloat16 on an RTX 4090); CPU support is listed as coming. The README describes it as intended for research and educational use. A successor, Dia2, lives in a separate repo (nari-labs/dia2).

- Repository: https://github.com/nari-labs/dia
- Official docs: https://github.com/nari-labs/dia#readme
- Checked: 2026-10-16

## What it replaces
- ElevenLabs: Speech generation, Voice cloning (partial). English only, dialogue-oriented; voices vary per run unless you use an audio prompt or fix the seed.
- Descript: Voice cloning, Speech generation (partial). Voice cloning and text-to-speech only; no transcript-based audio or video editing.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, on an NVIDIA GPU (CPU support not yet available) | https://github.com/nari-labs/dia#-hardware-and-inference-speed | 2026-10-15 |
| Code licence | Confirmed | Apache-2.0 | https://github.com/nari-labs/dia/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | Confirmed | Apache-2.0 (Dia-1.6B and Dia-1.6B-0626 on Hugging Face) | https://huggingface.co/nari-labs/Dia-1.6B-0626 | 2026-10-15 |
| Commercial use | Confirmed | Yes by licence (Apache-2.0 code and weights), though the README says the model is intended for research and educational use and forbids identity misuse and deceptive content | https://github.com/nari-labs/dia#%EF%B8%8F-disclaimer | 2026-10-15 |
| Paid services needed? | Confirmed | None required | https://github.com/nari-labs/dia#readme | 2026-10-15 |
| Hardware | Confirmed | NVIDIA GPU; about 4.4 GB VRAM in bfloat16/float16, about 7.9 GB in float32 (benchmarked on RTX 4090) | https://github.com/nari-labs/dia#-hardware-and-inference-speed | 2026-10-15 |
| Operating systems | Unknown | README lists Docker support for ARM and macOS as future work; it does not provide a verified native Windows/macOS/Linux support matrix | https://github.com/nari-labs/dia#readme | 2026-10-16 |
| Setup effort | Confirmed | Easy, pip install from GitHub (or uv), or via Hugging Face Transformers | https://github.com/nari-labs/dia#quickstart | 2026-10-15 |

GitHub: 19408 stars, 1689 forks, last push 2025-11-19, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/dia). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.