Qwen3-TTS实现3秒语音克隆，支持多语言实时合成与精细控制。
Qwen3-TTS Technical Report
- 采用双路径语言模型架构，结合两个语音分词器实现流式生成。
- 12Hz分词器延迟仅97毫秒，支持超低延迟首包输出。
- 开源模型与分词器，适合语音合成、智能交互等场景研究。
本文介绍Qwen3-TTS系列，这是一组先进的多语言、可控、鲁棒且支持流式传输的文本转语音模型。Qwen3-TTS支持业界领先的3秒语音克隆和基于描述的控制，可创建全新语音并精细调节输出音色。模型在超过500万小时跨10种语言的语音数据上训练，采用双路径语言模型架构实现实时合成，并配备两种语音分词器：1）Qwen-TTS-Tokenizer-25Hz为单码本编码器，强调语义内容，可无缝集成Qwen-Audio，通过块级DiT实现流式波形重建；2）Qwen-TTS-Tokenizer-12Hz采用12.5 Hz、16层多码本设计，实现极低码率与超低延迟，支持97毫秒内首包发射，搭配轻量级因果卷积网络。大量实验表明其在多种客观与主观基准（如TTS多语言测试集、InstructTTSEval及长语音测试集）上达到领先水平。为促进社区研究，我们以Apache 2.0许可证发布所有分词器与模型。
原文摘要 · Abstract (English)
In this report, we present the Qwen3-TTS series, a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control, allowing both the creation of entirely novel voices and fine-grained manipulation over the output speech. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS adopts a dual-track LM architecture for real-time synthesis, coupled with two speech tokenizers: 1) Qwen-TTS-Tokenizer-25Hz is a single-codebook codec emphasizing semantic content, which offers seamlessly integration with Qwen-Audio and enables streaming waveform reconstruction via a block-wise DiT. 2) Qwen-TTS-Tokenizer-12Hz achieves extreme bitrate reduction and ultra-low-latency streaming, enabling immediate first-packet emission ($97\,\mathrm{ms}$) through its 12.5 Hz, 16-layer multi-codebook design and a lightweight causal ConvNet. Extensive experiments indicate state-of-the-art performance across diverse objective and subjective benchmark (e.g., TTS multilingual test set, InstructTTSEval, and our long speech test set). To facilitate community research and development, we release both tokenizers and models under the Apache 2.0 license.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。