RedNote hilab · Text-to-Speech

dots.tts

2B-param fully continuous, end-to-end autoregressive TTS that skips discrete tokens, pairing a semantic encoder, an LLM and an autoregressive flow-matching acoustic head over a 48kHz AudioVAE. Cross-lingual voice cloning, emotional expressiveness and context-aware generation across 24 languages (0.94% WER Chinese, 83.9 avg speaker similarity); Apache-2.0.