mlsanityData to 7 Oct 2026

MOSS-TTS Technical Report

arXiv 2603.18090 ↗First posted 18 Mar 2026cs.SD cs.AI cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 63 of its 71 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

63 of 71 references.

References · 63

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2017Neural Discrete Representation Learningcited by 4,650
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  8. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  9. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  10. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  11. 2016Least Squares Generative Adversarial Networkscited by 1,000
  12. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
38 more
  1. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  2. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  3. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  4. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 694
  5. 2022High Fidelity Neural Audio Compressioncited by 673
  6. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  8. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 536
  9. 2020Scaling Laws for Autoregressive Generative Modelingcited by 510
  10. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  11. 2023Simple and Controllable Music Generationcited by 480
  12. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  13. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  14. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  15. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  16. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 323
  17. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  18. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
  19. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  20. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 165
  21. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 159
  22. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  23. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  24. 2025Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Soundcited by 129
  25. 2018AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scalecited by 125
  26. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 109
  27. 2026Qwen3-TTS Technical Reportcited by 106
  28. 2023SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Modelscited by 85
  29. 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 70
  30. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 69
  31. 2025Baichuan-Audio: A Unified Framework for End-to-End Speech Interactioncited by 68
  32. 2023Better speech synthesis through scalingcited by 63
  33. 2025MiMo-Audio: Audio Language Models are Few-Shot Learnerscited by 58
  34. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 48
  35. 2023AudioDec: An Open-source Streaming High-fidelity Neural Audio Codeccited by 47
  36. 2024BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codeccited by 45
  37. 2023FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codeccited by 44
  38. 2023Sparks of Large Audio Models: A Survey and Outlookcited by 41

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloningcited by 4
  2. 2026LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Spacecited by 3
  3. 2026WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modelingcited by 1
  4. 2026WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTScited by 1
  5. 2026EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillationcited by 0
  6. 2026CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latentscited by 0
  7. 2026Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encodercited by 0
  8. 2026Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesiscited by 0
  9. 2026Tokens Change, Structure Endures: Spectral Watermarking for Generated Speechcited by 0
  10. 2026Controlling Speaking Rate in Autoregressive TTS via Activation Steeringcited by 0