mlsanityData to 7 Oct 2026

Matcha-TTS: A fast TTS architecture with conditional flow matching

arXiv 2309.03199 ↗First posted 6 Sep 2023eess.AS cs.HC cs.LGcited by 142

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

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.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 35 of its 43 references that are in the map. First posted on arXiv 6 Sep 2023.

Builds on

35 of 43 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Better speech synthesis through scaling12 May
  2. 2023CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model11 May
  3. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models17 Nov
  4. 2022Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models17 Nov
  5. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech13 Jul
  6. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech13 May
  7. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 27

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  8. 2018Neural Ordinary Differential Equationscited by 3,733
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  10. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  11. 2018Self-Attention with Relative Position Representationscited by 1,112
  12. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
15 more
  1. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  2. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  3. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  4. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  5. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  6. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  7. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  8. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  9. 2021WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesiscited by 65
  10. 2022EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidancecited by 37
  11. 2021The Case for Translation-Invariant Self-Attention in Transformer-Based Language Modelscited by 23
  12. 2023Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesiscited by 13
  13. 2023Why We Should Report the Details in Subjective Evaluation of TTS More Rigorouslycited by 10
  14. 2021Neural HMMs are all you need (for high-quality attention-free TTS)cited by 8
  15. 2022OverFlow: Putting flows on top of neural transducers for better TTScited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 20; 2025: 69; 2026: 52.

142 papers.

Sort:

By area:

  1. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  2. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 323
  3. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  4. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  5. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 118
  6. 2025Baichuan-Omni-1.5 Technical Reportcited by 107
  7. 2025Baichuan-Audio: A Unified Framework for End-to-End Speech Interactioncited by 68
  8. 2024Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matchingcited by 52
  9. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  10. 2023Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesiscited by 29
  11. 2025IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech Systemcited by 27
  12. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
38 more
  1. 2024FlowTS: Time Series Generation via Rectified Flowcited by 22
  2. 2024Faces that Speak: Jointly Synthesising Talking Face and Speech from Textcited by 21
  3. 2024DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Datasetcited by 20
  4. 2024EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vectorcited by 19
  5. 2025FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matchingcited by 18
  6. 2025FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matchingcited by 17
  7. 2024CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversationscited by 15
  8. 2025CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matchingcited by 11
  9. 2024TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touchcited by 10
  10. 2025FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generationcited by 10
  11. 2025AV-Flow: Transforming Text to Audio-Visual Human-like Interactionscited by 9
  12. 2025From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speechcited by 9
  13. 2025C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversationscited by 9
  14. 2025FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matchingcited by 8
  15. 2025A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Datacited by 7
  16. 2025AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generationcited by 6
  17. 2025FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancingcited by 6
  18. 2025Step-Audio-EditX Technical Reportcited by 6
  19. 2025M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesiscited by 6
  20. 2024Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesiscited by 5
  21. 2025UniWav: Towards Unified Pre-training for Speech Representation Learning and Generationcited by 5
  22. 2025DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generationcited by 5
  23. 2025BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Modelscited by 5
  24. 2025Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modelingcited by 5
  25. 2025VoXtream: Full-Stream Text-to-Speech with Extremely Low Latencycited by 5
  26. 2024SF-Speech: Straightened Flow for Zero-Shot Voice Clonecited by 4
  27. 2025MusFlow: Multimodal Music Generation via Conditional Flow Matchingcited by 4
  28. 2025OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matchingcited by 4
  29. 2025FlowRec: Prior-Informed Flow Matching for Efficient Sequential Recommendation Generationcited by 4
  30. 2024LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesiscited by 3
  31. 2024FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Ratescited by 3
  32. 2025SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flowcited by 3
  33. 2025FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for "U-Tsang, Amdo and Kham Speech Dataset Generationcited by 3
  34. 2025No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTScited by 3
  35. 2025From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Trainingcited by 3
  36. 2025VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learningcited by 3
  37. 2025SyMuPe: Affective and Controllable Symbolic Music Performancecited by 3
  38. 2026FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenescited by 3

50 most cited of 142 All 142 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
  2. 2026dots.tts Technical Report
  3. 2026PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
  4. 2026FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation
  5. 2026End-to-End Training for Discrete Token LLM based TTS System
  6. 2025Drax: Speech Recognition with Discrete Flow Matching
  7. 2025A2TTS: TTS for Low Resource Indian Languages
  8. 2026DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis