Audio model

Dia 1.6B

Dia-1.6B is Nari Labs’ ultra-compact instruction model—about 1.6B parameters—built for fast, low-cost deployment on a single GPU or edge device. It handles everyday reasoning, summarization, and lightweight coding, with structured JSON outputs and tool/function calling for agents.

Type
Audio
Weights
Open
Downloads
29k
Likes
2.9k
Pipeline
text to speech
License
apache-2.0

Model hub

nari-labs/Dia-1.6B

Repo
nari-labs/Dia-1.6B
Access
Public
Technical tags and languages
en safetensors model_hub_mixin pytorch_model_hub_mixin text-to-speech
Open on Hugging Face

Papers

1

More from Nari Labs

4

About Nari Labs

1

Open-source TTS startup behind Dia, a 1.6B real-time, zero-shot voice-cloning model.