Matcha-tts: A Fast TTS Architecture With Conditional Flow Matching

Abstract

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.

Stats

• citations91
• S2 citations—
• github stars0
• HF likes0
• heat score14.73
• arxiv keymehta2023matcha

Related papers

• F5-TTS: A Fairytaler That Fakes Fluent And Faithful Speech With Flow Matching (2024)0.00
• Diflow-tts: Compact And Low-latency Zero-shot Text-to-speech With Factorized Discrete Flow Matching (2025)0.00
• Efficienttts: An Efficient And High-quality Text-to-speech Architecture (2020)0.00
• Mixer-tts: Non-autoregressive, Fast And Compact Text-to-speech Model Conditioned On Language Model Embeddings (2021)6.34
• Tangoflux: Super Fast And Faithful Text To Audio Generation With Flow Matching And Clap-ranked Preference Optimization (2024)0.00
• Glow-tts: A Generative Flow For Text-to-speech Via Monotonic Alignment Search (2020)0.00
• Unified Speech And Gesture Synthesis Using Flow Matching (2023)5.24
• Syncspeech: Efficient And Low-latency Text-to-speech Based On Temporal Masked Transformer (2025)0.00