# Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling

arXiv: https://arxiv.org/abs/2505.19669 · HTML: https://mlsanity.com/paper/2505.19669/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming](https://mlsanity.com/paper/2408.16725/) (2024)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling](https://mlsanity.com/paper/2303.03926/) (2023)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [Autoregressive Speech Synthesis without Vector Quantization](https://mlsanity.com/paper/2407.08551/) (2024)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment](https://mlsanity.com/paper/2406.07855/) (2024)
- [CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2404.02781/) (2024)
- [RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis](https://mlsanity.com/paper/2404.03204/) (2024)
- [LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes](https://mlsanity.com/paper/2406.02897/) (2024)
- [Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction](https://mlsanity.com/paper/2311.02898/) (2023)
- [Zero-Shot Text-to-Speech from Continuous Text Streams](https://mlsanity.com/paper/2410.00767/) (2024)
- [High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model](https://mlsanity.com/paper/2406.17310/) (2024)
- [TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer](https://mlsanity.com/paper/2501.06320/) (2025)

## Built on by (most cited first, 3 of 3)

- [StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling](https://mlsanity.com/paper/2506.12570/) (2025)
- [Next Tokens Denoising for Speech Synthesis](https://mlsanity.com/paper/2507.22746/) (2025)
- [Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input](https://mlsanity.com/paper/2603.06444/) (2026)

## Abstract (arXiv)

Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces high processing latency. To address this issue, we propose SMLLE, a streaming framework for generating high-quality speech frame-by-frame. SMLLE employs a Transducer to convert text into semantic tokens in real time while simultaneously obtaining duration alignment information. The combined outputs are then fed into a fully autoregressive (AR) streaming model to reconstruct mel-spectrograms. To further stabilize the generation process, we design a Delete < Bos > Mechanism that allows the AR model to access future text introducing as minimal delay as possible. Experimental results suggest that the SMLLE outperforms current streaming TTS methods and achieves comparable performance over sentence-level TTS systems. Samples are available on shy-98.github.io/SMLLE_demo_page/.