nari-labs/Dia-1.6B-0626
text-to-speech model by nari-labs
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration. Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc. To accelerate research, we are providing access to pretrained model checkpoints and inference code. The model weights are hosted on Hugging Face. The model only supports English generation at the moment. We also provide a demo page comparing our model to ElevenLabs Studio and Sesame CSM-1B. This will open a Gradio UI that you can work on. or if you do not have uv pre-installed: Note that the model was not fine-tuned on a specific voice. Hence, you will get different voices every time you run the model. You can keep speaker consistency…
Read the full model card ↗ · Preview checked 2026-10-28T16:36:05.552Z
Inside the original model card — Document outline
- ⚡️ Quickstart
- Features
- ⚙️ Usage
- As a Python Library
- As part of transformers
- Generation with Text
- Generation with Text and Audio (Voice Cloning)
- 💻 Hardware and Inference Speed
- 🪪 License
- ⚠️ Disclaimer
- 🔭 TODO / Future Work
- 🤝 Contributing
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
nari-labs/Dia-1.6B-0626 is a text-to-speech model repository published by nari-labs on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- Not reported
- Recent downloads (30 days)
- 14,848
- Cumulative likes
- 134
- Hugging Face trending score
- 1
- Reported safetensors parameters
- 1,611,160,576
- Architecture
- DiaForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2025-06-26T13:44:11.000Z
- Last modified
- 2025-07-03T14:45:09.000Z
Compatibility and lineage
Reported languages: en
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-30T06:51:23.807Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.