We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion decoder, enabling parallel token generation within each block while retaining block-by-block streaming. We find that naively transferring mainstream block-diffusion decoding to discrete speech tokens degrades quality, as a long-tail token distribution biases parallel position selection toward a few high-frequency tokens. To mitigate this without architectural modification, we introduce two inference-time techniques: prior-calibrated scoring, which subtracts the block-level marginal token distribution, and an early-decoding schedule, which adaptively terminates iteration based on calibrated confidence. On standard zero-shot TTS benchmarks, Chatterbox-Flash attains high-fidelity synthesis comparable to strong autoregressive and non-autoregressive baselines, while supporting streaming inference with time-to-first-packet on par with streaming AR systems and substantially lower real-time factor. Code and audio samples are available at https://github.com/resemble-ai/chatterbox-flash.

翻译：我们提出Chatterbox-Flash——一种通过将预训练自回归TTS解码器微调为块扩散解码器而获得的零样本文语合成模型，可在每个块内实现并行令牌生成，同时保持逐块流式处理。我们发现，简单地将主流块扩散解码迁移到离散语音令牌会降低质量，因为长尾令牌分布会使并行位置选择偏向少数高频令牌。为在不修改架构的前提下缓解此问题，我们引入两项推理时技术：先验校准评分（减去块级别边际令牌分布）和早期解码调度（基于校准置信度自适应终止迭代）。在标准零样本TTS基准测试中，Chatterbox-Flash在合成高保真度方面可与强自回归和非自回归基线方法媲美，同时支持流式推理，其首包延迟与流式自回归系统相当，且实时因子显著降低。代码和音频样本见https://github.com/resemble-ai/chatterbox-flash。