Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

VoXtream2: Full-stream TTS with dynamic speaking rate control

About

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.

Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze• 2026

Related benchmarks

TaskDatasetResultRank
Text-to-SpeechSeed-TTS en (test)
WER1.32
90
Text-to-SpeechLibriSpeech PC clean (test)
WER2.12
31
Text-to-SpeechEmilia EN speaking-rate
MUSHRA Score68.8
9
Showing 3 of 3 rows

Other info

Follow for update