TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment

A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.

---

Text-Acoustic Dual-Alignment Large Language Model

TADA is a unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. By leveraging a novel tokenizer and architectural design, TADA achieves high-fidelity synthesis and generation with a fraction of the computational overhead required by traditional models.

⭐️ arxiv: https://arxiv.org/abs/2602.23068
⭐️ demo1: https://huggingface.co/spaces/fffiloni/tada-dual-alignment-tts-demo
⭐️ demo2: https://huggingface.co/spaces/HumeAI/tada
⭐️ github: https://github.com/HumeAI/tada
⭐️ blog post: https://www.hume.ai/blog/opensource-tada