# MOSS-TTSD: Text to Spoken Dialogue Generation

arXiv: https://arxiv.org/abs/2603.19739 · HTML: https://mlsanity.com/paper/2603.19739/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://mlsanity.com/paper/2502.04128/) (2025)
- [MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation](https://mlsanity.com/paper/2312.11825/) (2023)
- [FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot](https://mlsanity.com/paper/2509.02020/) (2025)
- [VibeVoice Technical Report](https://mlsanity.com/paper/2508.19205/) (2025)
- [MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models](https://mlsanity.com/paper/2602.10934/) (2026)

## Built on by (most cited first, 2 of 2)

- [KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction](https://mlsanity.com/paper/2609.07200/) (2026)
- [OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents](https://mlsanity.com/paper/2609.32569/) (2026)

## Abstract (arXiv)

Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate turn-taking, cross-turn acoustic consistency, and long-form stability, which current models often fail to address due to a lack of dialogue context modeling. To bridge this gap, we present MOSS-TTSD, a spoken dialogue synthesis model designed for expressive, multi-party conversational speech across multiple languages. With enhanced long-context modeling, MOSS-TTSD generates long-form spoken conversations from dialogue scripts with explicit speaker tags, supporting up to 60 minutes of single-pass synthesis, multi-party dialogue with up to 5 speakers, and zero-shot voice cloning from a short reference audio clip. The model supports various mainstream languages, including English and Chinese, and is adapted to several long-form scenarios. Additionally, to address limitations of existing evaluation methods, we propose TTSD-eval, an objective evaluation framework based on forced alignment that measures speaker attribution accuracy and speaker similarity without relying on speaker diarization tools. Both objective and subjective evaluation results show that MOSS-TTSD surpasses strong open-source and proprietary baselines in dialogue synthesis.