PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
It addresses cross-lingual voice cloning for TTS applications, offering robust performance with short reference audio and no extra training, though it appears incremental as it builds on existing flow-matching methods.
The paper tackled the stability-naturalness trade-off, weak cross-lingual voice cloning, and limited audio quality in flow-matching TTS by proposing PFluxTTS, which achieved a MOS of 4.11 in naturalness, 23% lower WER (6.9% vs. 9.0%), and +0.32 SMOS in speaker similarity compared to baselines.
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 https://braskai.github.io/pfluxtts/