# FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System

arXiv: https://arxiv.org/abs/2503.20499 · HTML: https://mlsanity.com/paper/2503.20499/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2025.

## Built on by (most cited first, 6 of 6)

- [XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models](https://mlsanity.com/paper/2510.15148/) (2025)
- [VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency](https://mlsanity.com/paper/2509.15969/) (2025)
- [LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space](https://mlsanity.com/paper/2603.29339/) (2026)
- [DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech](https://mlsanity.com/paper/2607.04140/) (2026)
- [RWKVTTS: Yet another TTS based on RWKV-7](https://mlsanity.com/paper/2504.03289/) (2025)
- [E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis](https://mlsanity.com/paper/2511.07099/) (2025)

## Abstract (arXiv)

In this work, we upgrade FireRedTTS to a new version, FireRedTTS-1S, a high-quality streaming foundation text-to-speech system. FireRedTTS-1S achieves streaming speech generation via two steps: text-to-semantic decoding and semantic-to-acoustic decoding. In text-to-semantic decoding, a semantic-aware speech tokenizer converts the speech signal into semantic tokens, which can be synthesized from the text via a language model in an auto-regressive manner. Meanwhile, the semantic-to-acoustic decoding module simultaneously translates generated semantic tokens into the speech signal in a streaming way. We implement two approaches to achieve this module: 1) a chunk-wise streamable flow-matching approach, and 2) a multi-stream language model-based approach. They both present high-quality and streamable speech generation but differ in real-time factor (RTF) and latency. Specifically, flow-matching decoding can generate speech by chunks, presenting a lower RTF of 0.1 but a higher latency of 300ms. Instead, the multi-stream language model generates speech by frames in an autoregressive manner, presenting a higher RTF of 0.3 but a low latency of 150ms. In experiments on zero-shot voice cloning, the objective results validate FireRedTTS-1S as a high-quality foundation model with comparable intelligibility and speaker similarity over industrial baseline systems. Furthermore, the subjective score of FireRedTTS-1S highlights its impressive synthesis performance, achieving comparable quality to the ground-truth recordings. These results validate FireRedTTS-1S as a high-quality streaming foundation TTS system.