VoXtream2: Full-stream TTS with dynamic speaking rate control
This work addresses the need for low-latency, controllable TTS in interactive applications, representing an incremental improvement over existing methods.
The paper tackles the problem of full-stream text-to-speech for interactive systems, requiring minimal delay and controllability as text arrives incrementally, and presents VoXtream2, which achieves competitive results on benchmarks with 4 times faster than real-time performance and 74 ms first-packet latency.
Full-stream text-to-speech (TTS) for interactive systems must start speaking with minimal delay while remaining controllable as text arrives incrementally. We present VoXtream2, a zero-shot full-stream TTS model with dynamic speaking-rate control that can be updated mid-utterance on the fly. VoXtream2 combines a distribution matching mechanism over duration states with classifier-free guidance across conditioning signals to improve controllability and synthesis quality. Prompt-text masking enables textless audio prompting, removing the need for prompt transcription. Across standard zero-shot benchmarks and a dedicated speaking-rate test set, VoXtream2 achieves competitive objective and subjective results against public baselines despite a smaller model and less training data. In full-stream mode, it runs 4 times faster than real time with 74 ms first-packet latency on a consumer GPU.