MOSS-TTS Technical Report

• URL: http://arxiv.org/abs/2603.18090v2
• Date: Fri, 20 Mar 2026 08:16:20 GMT
• Title: MOSS-TTS Technical Report
• Abstract summary: MOSS-TTS is a speech generation foundation model built on a scalable recipe.<n>It compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations.<n>It supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation.
• Score: 62.0595749527453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Qwen3-TTS Technical Report [64.94647392030824]
  We present the Qwen3-TTS series, a family of advanced multilingual, controllable, robust, and streaming text-to-speech models.<n>Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.<n>Qwen3-TTS adopts a dual-track LM architecture for real-time synthesis, coupled with two speech tokenizers.
  arXiv  Detail & Related papers  (2026-01-22T03:51:43Z)
• Step-Audio-EditX Technical Report [61.039849674472585]
  We present Step-Audio-EditX, the first open-source LLM-based audio model excelling at expressive and iterative audio editing.<n>Our core innovation lies in leveraging only large-margin synthetic data, which circumvents the need for embedding-based priors or auxiliary modules.<n> Evaluation results demonstrate that Step-Audio-EditX surpasses both MiniMax-2.6-hd and Doubao-Seed-TTS-2.0 in emotion editing and other fine-grained control tasks.
  arXiv  Detail & Related papers  (2025-11-05T16:22:19Z)
• VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model [84.25283710008785]
  VITA-Audio is an end-to-end large speech model with fast audio-text token generation.<n>MCTP module efficiently generates multiple audio tokens within a single model forward pass.<n>Four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality.
  arXiv  Detail & Related papers  (2025-05-06T17:59:53Z)
• Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens [31.575335190916995]
  We introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech that decomposes speech into two complementary token types.<n>To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations.
  arXiv  Detail & Related papers  (2025-03-03T16:23:10Z)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis [6.509758931804479]
  We propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. FastPitchFormant has a unique structure that handles text and acoustic features in parallel.
  arXiv  Detail & Related papers  (2021-06-29T07:06:42Z)
• Many-to-Many Voice Transformer Network [55.17770019619078]
  This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework. It enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech.
  arXiv  Detail & Related papers  (2020-05-18T04:02:08Z)
• Serialized Output Training for End-to-End Overlapped Speech Recognition [35.894025054676696]
  serialized output training (SOT) is a novel framework for multi-speaker overlapped speech recognition. SOT uses a model with only one output layer that generates the transcriptions of multiple speakers one after another. We show that the SOT models can transcribe overlapped speech with variable numbers of speakers significantly better than PIT-based models.
  arXiv  Detail & Related papers  (2020-03-28T02:37:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.