Dia is a 1.6B parameter text to speech model created by Nari Labs.

UPDATE 🤗(06/27): Dia is now available through Hugging Face Transformers!

UPDATE 🚀(11/19): Dia2 is released on Github and HuggingFace link!

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.

• We have a ZeroGPU Space running! Try it now here. Thanks to the HF team for the support :)
• Join our discord server for community support and access to new features.
• Play with a larger version of Dia: generate fun conversations, remix content, and share with friends. 🔮 Join the waitlist for early access.

Generation Guidelines

• Keep input text length moderate
• Short input (corresponding to under 5s of audio) will sound unnatural
• Very long input (corresponding to over 20s of audio) will make the speech unnaturally fast.
• Use non-verbal tags sparingly, from the list in the README. Overusing or using unlisted non-verbals may cause weird artifacts.
• Always begin input text with [S1], and always alternate between [S1] and [S2] (i.e. [S1]... [S1]... is not good)
• When using audio prompts (voice cloning), follow these instructions carefully:
• Provide the transcript of the to-be cloned audio before the generation text.
• Transcript must use [S1], [S2] speaker tags correctly (i.e. single speaker: [S1]..., two speakers: [S1]... [S2]...)
• Duration of the to-be cloned audio should be 5~10 seconds for the best results.

• Put [S1] or [S2] (the second-to-last speaker's tag) at the end of the audio to improve audio quality at the end

Quickstart

Transformers Support

We now have a Hugging Face Transformers implementation of Dia! You should install main branch of transformers to use it. See hf.py for more information.

pip install git+https://github.com/huggingface/transformers.git
or install with uv
uv pip install git+https://github.com/huggingface/transformers.git

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")

# Clone this repository
git clone https://github.com/nari-labs/dia.git
cd dia
Optionally
python -m venv .venv && source .venv/bin/activate
Install dia
pip install -e .

# Install directly from GitHub
pip install git+https://github.com/nari-labs/dia.git

python example/simple.py

# Clone this repository
git clone https://github.com/nari-labs/dia.git
cd dia

uv run example/simple.py

python app.py
Or if you have uv installed
uv run app.py

python cli.py --help
Or if you have uv installed
uv run cli.py --help

This project offers a high-fidelity speech generation model intended for research and educational use. The following uses are strictly forbidden:

• Identity Misuse: Do not produce audio resembling real individuals without permission.
• Deceptive Content: Do not use this model to generate misleading content (e.g. fake news)
• Illegal or Malicious Use: Do not use this model for activities that are illegal or intended to cause harm.

🔭 TODO / Future Work

• Docker support for ARM architecture and MacOS.
• Optimize inference speed.
• Add quantization for memory efficiency.

🤝 Contributing

We are a tiny team of 1 full-time and 1 part-time research-engineers. We are extra-welcome to any contributions! Join our Discord Server for discussions.

🤗 Acknowledgements

• We thank the Google TPU Research Cloud program for providing computation resources.
• Our work was heavily inspired by SoundStorm, Parakeet, and Descript Audio Codec.
• Hugging Face for providing the ZeroGPU Grant.
• "Nari" is a pure Korean word for lily.
• We thank Jason Y. for providing help with data filtering.

⭐ Star History