Xiaohongshu Tech REDtech

Aug 13, 2026 · Artificial Intelligence

dots.tts: Open‑Source Continuous Autoregressive TTS Model for Sustainable, Scalable Voice Synthesis

dots.tts is a 2‑billion‑parameter, fully continuous, end‑to‑end autoregressive TTS model released by the Xiaohongshu dots team, offering state‑of‑the‑art zero‑shot voice cloning, low‑step inference, 1‑to‑1 audio‑text streaming, and an extensible training pipeline for research and deployment.