mlsanityData to 7 Oct 2026

RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching

arXiv 2506.16741 ↗First posted 20 Jun 2025eess.AS cs.AIcited by 1

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

Abstract (arXiv)

We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves natural-quality speech, it typically requires a large number of generation steps, resulting in a trade-off between quality and inference speed. To address this challenge, RapFlow-TTS enforces consistency in the velocity field along the FM-straightened ODE trajectory, enabling consistent synthetic quality with fewer generation steps. Additionally, we introduce techniques such as time interval scheduling and adversarial learning to further enhance the quality of the few-step synthesis. Experimental results show that RapFlow-TTS achieves high-fidelity speech synthesis with a 5- and 10-fold reduction in synthesis steps than the conventional FM- and score-based approaches, respectively.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 26 of its 30 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

26 of 30 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching10 Sep
  2. 2023Matcha-TTS: A fast TTS architecture with conditional flow matching6 Sep
  3. 2023CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model11 May
  4. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech13 May
  5. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr

Other references · 21

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2023Consistency Modelscited by 1,778
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  9. 2016Least Squares Generative Adversarial Networkscited by 1,000
  10. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  11. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  12. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
9 more
  1. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  2. 2023Improved Techniques for Training Consistency Modelscited by 430
  3. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  4. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 189
  5. 2024Improving the Training of Rectified Flowscited by 106
  6. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistencycited by 101
  7. 2024Simple ReFlow: Improved Techniques for Fast Flow Modelscited by 34
  8. 2022StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesiscited by 32
  9. 2024DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variabilitycited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Flamed-TTS: Flow Matching Attention-Free Models for Efficient Generating and Dynamic Pacing Zero-shot Text-to-Speechcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
  2. 2025Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
  3. 2024CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
  4. 2025Towards Flow-Matching-based TTS without Classifier-Free Guidance
  5. 2025Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis
  6. 2026BareWave: Waveform-Native Flow-Matching Text-to-Speech
  7. 2023ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech
  8. 2026Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis