# Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm

arXiv: https://arxiv.org/abs/2607.23938 · HTML: https://mlsanity.com/paper/2607.23938/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2026.

## Built on by (most cited first, 5 of 5)

- [Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder](https://mlsanity.com/paper/2608.11650/) (2026)
- [NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2609.27086/) (2026)
- [WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection](https://mlsanity.com/paper/2609.29372/) (2026)
- [SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS](https://mlsanity.com/paper/2609.39088/) (2026)
- [JoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation](https://mlsanity.com/paper/2610.08834/) (2026)

## Abstract (arXiv)

In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, audio quality, controllability, multilingual coverage, efficiency, and robustness. It combines a 12.5~Hz low-frame-rate speech tokenizer for reduced inference latency with a five-stage progressive training paradigm for coordinated language model (LM) and flow-matching model (FM) optimization. The model provides production-level control through free-style natural-language instructions and fine-grained inline tags, while supporting 16 languages, 20 Chinese dialect regions, one-pass long-form synthesis up to 3 minutes, and robust generation from noisy, reverberant, or unclear reference speech. Across SEED-TTS-Eval, CV3-Eval, instruction-following, long-form, and acoustic-robustness evaluations, Qwen-Audio-3.0-TTS achieves state-of-the-art performance on many reported dimensions or the strongest aggregate results. It also ranks first on the independent Artificial Analysis Text-to-Speech Leaderboard. These results establish Qwen-Audio-3.0-TTS as a strong foundation for production-level speech synthesis.