FlowEdit: Lifelong Pronunciation Adaptation in Flow-Matching TTS

FlowEdit introduces a lifelong pronunciation adaptation framework for frozen Flow-Matching TTS models using associative memory, enabling persistent corrections to out-of-vocabulary words without retraining.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementJun 18, 2026, 05:36 PM 84%

   FlowEdit framework enables lifelong pronunciation corrections in Flow-Matching TTS using associative memory

   FlowEdit introduces a lifelong pronunciation adaptation framework for frozen Flow-Matching TTS models using associative memory, enabling persistent corrections to out-of-vocabulary words without retraining.

   Read the full story →