Matcha-TTS: A fast TTS architecture with conditional flow matching
This work addresses the need for faster and high-quality text-to-speech synthesis for applications requiring real-time or efficient speech generation, representing a strong specific gain rather than a foundational breakthrough.
The authors tackled the problem of slow text-to-speech synthesis by introducing Matcha-TTS, an encoder-decoder architecture trained with optimal-transport conditional flow matching, which achieves high output quality in fewer synthesis steps and attains the highest mean opinion score in listening tests compared to strong baselines.
We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic modelling, trained using optimal-transport conditional flow matching (OT-CFM). This yields an ODE-based decoder capable of high output quality in fewer synthesis steps than models trained using score matching. Careful design choices additionally ensure each synthesis step is fast to run. The method is probabilistic, non-autoregressive, and learns to speak from scratch without external alignments. Compared to strong pre-trained baseline models, the Matcha-TTS system has the smallest memory footprint, rivals the speed of the fastest models on long utterances, and attains the highest mean opinion score in a listening test. Please see https://shivammehta25.github.io/Matcha-TTS/ for audio examples, code, and pre-trained models.