Abstract
We present PFluxTTS, a hybrid text-to-speech system addressing three gaps in flow-matching TTS: the stability-naturalness trade-off, weak cross-lingual voice cloning, and limited audio quality from low-rate mel features. Our contributions are: (1) a dual-decoder design combining duration-guided and alignment-free models through inference-time vector-field fusion; (2) robust cloning using a sequence of speech-prompt embeddings in a FLUX-based decoder, preserving speaker traits across languages without prompt transcripts; and (3) a modified PeriodWave vocoder with super-resolution to 48 kHz. On cross-lingual in-the-wild data, PFluxTTS clearly outperforms F5-TTS, FishSpeech, and SparkTTS, matches ChatterBox in naturalness (MOS 4.11) while achieving 23% lower WER (6.9% vs. 9.0%), and surpasses ElevenLabs in speaker similarity (+0.32 SMOS). The system remains robust in challenging scenarios where most open-source models fail, while requiring only short reference audio and no extra training. Audio demos are available at this https URL
Abstract (translated)
我们介绍了一种名为PFluxTTS的混合文本到语音系统，该系统解决了流匹配型文本转语音技术中的三大不足：稳定性与自然度之间的权衡、跨语言声音克隆能力弱以及低采样率梅尔特征导致的音频质量受限。我们的贡献包括： 1. 设计了一种双解码器架构，通过推理时向量场融合将持续时间指导型和对齐自由型模型结合在一起。 2. 使用FLUX基础解码器中的语音提示嵌入序列进行鲁棒性克隆，在没有提示转录的情况下也能跨语言保留说话人的特性。 3. 对PeriodWave编码器进行了修改，使其能够实现超分辨率至48kHz。 在多语种真实场景数据集上，PFluxTTS明显优于F5-TTS、FishSpeech和SparkTTS，并且与ChatterBox一样自然（MOS为4.11），但错误率降低了23%（WER从9.0%降至6.9%）。此外，在说话人相似度方面，PFluxTTS超过了ElevenLabs（SMOS增加+0.32）。 该系统在大多数开源模型无法胜任的困难场景中仍然保持稳健表现，并且只需短参考音频和无需额外训练。音频演示可在以下网址获取：[此URL]
URL
https://arxiv.org/abs/2602.04160
