Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions

About

This study proposes FlexiVoice, a text-to-speech (TTS) synthesis system capable of flexible style control with zero-shot voice cloning. The speaking style is controlled by a natural-language instruction and the voice timbre is provided by a speech reference in zero-shot manner. FlexiVoice is built with an LLM core, which takes text as input, and also takes an optional natural language instruction and an optional speech reference to control style and timbre, respectively. FlexiVoice is equipped with a novel Progressive Post-Training (PPT) scheme that progressively unlocks accurate and flexible controllability. In particular, it first employs Direct Preference Optimization (DPO) to enable FlexiVoice to accurately follow both natural language instruction and speech reference simultaneously. It then uses a multi-objective Group Relative Policy Optimization (GRPO) to disentangle style instruction, reference timbre, and textual content. Finally, it adapts instruction GRPO for more advanced instruction following. Experimental results show that FlexiVoice surpasses competing baselines and demonstrates strong capability in decoupling control factors. Human evaluations further confirm its naturalness, controllability, and robustness. Audio samples are available at https://flexi-voice.github.io.

Dekun Chen, Xueyao Zhang, Yuancheng Wang, Kenan Dai, Li Ma, Zhizheng Wu• 2026

Related benchmarks

TaskDatasetResultRank
Complex Instruction FollowingInstructTTSEval EN
APS81.2
12
Complex Instruction FollowingInstructTTSEval ZH
APS71
8
Text-to-Speech (Text-Only input)Emotion TTS (EN) Easy
ACC-I97.4
7
Pitch ControlEnglish Speech 1.0 (test)
Spearman Correlation91
6
Speaking Speed ControlEnglish Speech 1.0 (test)
Spearman Correlation Coefficient0.86
6
Text-to-Speech (Text-Only input)Emotion TTS (EN) (Hard)
ACC-I89.4
6
Text-to-Speech (Text and Reference Speech input)Emotion TTS (ZH) Easy
ACC-I81.8
5
Text-to-Speech (Text and Reference Speech input)Emotion TTS (ZH) (Hard)
ACC-I75.8
5
Text and Reference Speech SynthesisFirst evaluation set ZH Easy
WER3.08
5
Text-to-Speech (Text and Reference Speech input)Emotion TTS (EN) Easy
ACC-I89.4
5
Showing 10 of 20 rows

Other info

Follow for update