# CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model

arXiv: https://arxiv.org/abs/2305.06908 · HTML: https://mlsanity.com/paper/2305.06908/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 11 May 2023.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions](https://mlsanity.com/paper/2209.11215/) (2022)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)
- [DDP: Diffusion Model for Dense Visual Prediction](https://mlsanity.com/paper/2303.17559/) (2023)
- [Monocular Depth Estimation using Diffusion Models](https://mlsanity.com/paper/2302.14816/) (2023)
- [Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent](https://mlsanity.com/paper/2302.09057/) (2023)
- [Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis](https://mlsanity.com/paper/2201.07429/) (2022)
- [DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs](https://mlsanity.com/paper/2201.11972/) (2022)
- [HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis](https://mlsanity.com/paper/2009.01776/) (2020)
- [DurIAN: Duration Informed Attention Network For Multimodal Synthesis](https://mlsanity.com/paper/1909.01700/) (2019)
- [XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System](https://mlsanity.com/paper/2006.06261/) (2020)
- [ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech](https://mlsanity.com/paper/2212.14518/) (2022)

## Built on by (most cited first, 30 of 45)

- [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://mlsanity.com/paper/2309.03199/) (2023)
- [VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching](https://mlsanity.com/paper/2309.05027/) (2023)
- [HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis](https://mlsanity.com/paper/2311.12454/) (2023)
- [Autoregressive Diffusion Transformer for Text-to-Speech Synthesis](https://mlsanity.com/paper/2406.05551/) (2024)
- [Music2Latent: Consistency Autoencoders for Latent Audio Compression](https://mlsanity.com/paper/2408.06500/) (2024)
- [Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis](https://mlsanity.com/paper/2312.03491/) (2023)
- [ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching](https://mlsanity.com/paper/2506.13053/) (2025)
- [FlashSpeech: Efficient Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2404.14700/) (2024)
- [LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation](https://mlsanity.com/paper/2406.08203/) (2024)
- [ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation](https://mlsanity.com/paper/2309.10740/) (2023)
- [ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech](https://mlsanity.com/paper/2309.17056/) (2023)
- [AudioLCM: Text-to-Audio Generation with Latent Consistency Models](https://mlsanity.com/paper/2406.00356/) (2024)
- [CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models](https://mlsanity.com/paper/2404.00569/) (2024)
- [CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems](https://mlsanity.com/paper/2407.12676/) (2024)
- [CoMoSVC: Consistency Model-based Singing Voice Conversion](https://mlsanity.com/paper/2401.01792/) (2024)
- [Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding](https://mlsanity.com/paper/2410.13839/) (2024)
- [E1 TTS: Simple and Fast Non-Autoregressive TTS](https://mlsanity.com/paper/2409.09351/) (2024)
- [StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion](https://mlsanity.com/paper/2409.10058/) (2024)
- [CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio](https://mlsanity.com/paper/2509.09836/) (2025)
- [Efficient Text-driven Motion Generation via Latent Consistency Training](https://mlsanity.com/paper/2405.02791/) (2024)
- [FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation](https://mlsanity.com/paper/2405.07682/) (2024)
- [DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability](https://mlsanity.com/paper/2406.19135/) (2024)
- [DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2410.11097/) (2024)
- [DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles](https://mlsanity.com/paper/2412.03388/) (2024)
- [FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation](https://mlsanity.com/paper/2501.10807/) (2025)
- [Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization](https://mlsanity.com/paper/2408.08019/) (2024)
- [Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding](https://mlsanity.com/paper/2501.17578/) (2025)
- [LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis](https://mlsanity.com/paper/2407.10468/) (2024)
- [SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow](https://mlsanity.com/paper/2504.07776/) (2025)
- [Inference-time Scaling for Diffusion-based Audio Super-resolution](https://mlsanity.com/paper/2508.02391/) (2025)

## Abstract (arXiv)

Denoising diffusion probabilistic models (DDPMs) have shown promising performance for speech synthesis. However, a large number of iterative steps are required to achieve high sample quality, which restricts the inference speed. Maintaining sample quality while increasing sampling speed has become a challenging task. In this paper, we propose a "Co"nsistency "Mo"del-based "Speech" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality. The consistency constraint is applied to distill a consistency model from a well-designed diffusion-based teacher model, which ultimately yields superior performances in the distilled CoMoSpeech. Our experiments show that by generating audio recordings by a single sampling step, the CoMoSpeech achieves an inference speed more than 150 times faster than real-time on a single NVIDIA A100 GPU, which is comparable to FastSpeech2, making diffusion-sampling based speech synthesis truly practical. Meanwhile, objective and subjective evaluations on text-to-speech and singing voice synthesis show that the proposed teacher models yield the best audio quality, and the one-step sampling based CoMoSpeech achieves the best inference speed with better or comparable audio quality to other conventional multi-step diffusion model baselines. Audio samples are available at https://comospeech.github.io/.