# Zero-Shot Text-to-Speech from Continuous Text Streams

arXiv: https://arxiv.org/abs/2410.00767 · HTML: https://mlsanity.com/paper/2410.00767/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2024.

## Built on by (most cited first, 7 of 7)

- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [SpeakStream: Streaming Text-to-Speech with Interleaved Data](https://mlsanity.com/paper/2505.19206/) (2025)
- [VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency](https://mlsanity.com/paper/2509.15969/) (2025)
- [Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling](https://mlsanity.com/paper/2505.19669/) (2025)
- [SyncSpeech: Efficient and Low-Latency Text-to-Speech based on Temporal Masked Transformer](https://mlsanity.com/paper/2502.11094/) (2025)
- [SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation](https://mlsanity.com/paper/2509.01200/) (2025)
- [Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input](https://mlsanity.com/paper/2603.06444/) (2026)

## Abstract (arXiv)

Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive continuously in short chunks, necessitating instant responses from the system. We identify the essential capabilities required for chunk-level streaming and introduce LiveSpeech 2, a stream-aware model that supports infinitely long speech generation, text-audio stream synchronization, and seamless transitions between short speech chunks. To achieve these, we propose (1) adopting Mamba, a class of sequence modeling distinguished by linear-time decoding, which is augmented by cross-attention mechanisms for conditioning, (2) utilizing rotary positional embeddings in the computation of cross-attention, enabling the model to process an infinite text stream by sliding a window, and (3) decoding with semantic guidance, a technique that aligns speech with the transcript during inference with minimal overhead. Experimental results demonstrate that our models are competitive with state-of-the-art language model-based zero-shot TTS models, while also providing flexibility to support a wide range of streaming scenarios.