# M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesis

arXiv: https://arxiv.org/abs/2512.04720 · HTML: https://mlsanity.com/paper/2512.04720/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 29 of its 30 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://mlsanity.com/paper/2406.18009/) (2024)
- [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://mlsanity.com/paper/2309.03199/) (2023)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching](https://mlsanity.com/paper/2506.13053/) (2025)
- [VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design](https://mlsanity.com/paper/2307.16430/) (2023)
- [Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding](https://mlsanity.com/paper/2307.15484/) (2023)
- [VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing](https://mlsanity.com/paper/2408.05758/) (2024)
- [Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling](https://mlsanity.com/paper/2505.19931/) (2025)
- [SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec](https://mlsanity.com/paper/2508.02849/) (2025)
- [InstructAudio: Unified speech and music generation with natural language instruction](https://mlsanity.com/paper/2511.18487/) (2025)

## Built on by (most cited first, 6 of 6)

- [MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning](https://mlsanity.com/paper/2601.01568/) (2026)
- [Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis](https://mlsanity.com/paper/2601.13802/) (2026)
- [UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions](https://mlsanity.com/paper/2604.22209/) (2026)
- [WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling](https://mlsanity.com/paper/2606.03455/) (2026)
- [Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion](https://mlsanity.com/paper/2603.14032/) (2026)
- [ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching](https://mlsanity.com/paper/2607.12496/) (2026)

## Abstract (arXiv)

Non-autoregressive (NAR) text-to-speech synthesis relies on length alignment between text sequences and audio representations, constraining naturalness and expressiveness. Existing methods depend on duration modeling or pseudo-alignment strategies that severely limit naturalness and computational efficiency. We propose M3-TTS, a concise and efficient NAR TTS paradigm based on multi-modal diffusion transformer (MM-DiT) architecture. M3-TTS employs joint diffusion transformer layers for cross-modal alignment, achieving stable monotonic alignment between variable-length text-speech sequences without pseudo-alignment requirements. Single diffusion transformer layers further enhance acoustic detail modeling. The framework integrates a mel-vae codec that provides 3* training acceleration. Experimental results on Seed-TTS and AISHELL-3 benchmarks demonstrate that M3-TTS achieves state-of-the-art NAR performance with the lowest word error rates (1.36% English, 1.31% Chinese) while maintaining competitive naturalness scores. Code and demos will be available at https://wwwwxp.github.io/M3-TTS.