让对话系统实时响应用户插话，语音生成又快又自然。
VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents
- 直接接收大模型文本流，支持连续语音生成
- 插话时立即中断，不重置缓存，延迟极低
- 保持高音质且可模块化，适合智能助手等场景
语音对话是人机交互的自然方式，但多数语音语言模型仍局限于回合制操作，缺乏实时响应能力（如用户插话）。现有双工语音到语音/语音到文本模型虽降低延迟，但常因需联合优化自动语音识别、插话处理与高保真合成，导致音质下降。本文提出 VoiceChat-TTS，一种面向交互式代理的低延迟、连续、可流式处理的文本转语音模型。该模型直接接收大语言模型的文本令牌流，通过控制令牌显式支持插话，并在无输入时生成静音。模型实现始终在线、快速响应的语音生成，同时保持模块化与高质量语音输出，支持语句中途插话而不重置键值缓存。
原文摘要 · Abstract (English)
Spoken dialogue is a natural form of human--computer interaction, yet most speech language models remain limited to turn-based operation and lack real-time adaptability, such as user barge-in. Recent duplex speech-to-speech and speech-to-text models reduce latency by replacing multi-stage pipelines, but often compromise speech quality because accurate ASR, interruption handling, and high-fidelity synthesis must be optimized jointly. We propose VoiceChat-TTS, a low-latency, continuous, and streamable text-to-speech model for interactive agents. VoiceChat-TTS is driven directly by LLM text-token streams, supports explicit interruption via control tokens, and produces silence when no textual input is available. The model enables always-on, responsive speech generation while preserving modularity and high speech quality, and it supports mid-utterance interruptions without resetting the KV cache.
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。