Metraipolis › archive › dc_e16ad00bca95

VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents — arXiv:2608.13831

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13831
License (as archived)
CC0-1.0
Archived
2026-10-19T02:27:59.794Z
SHA-256 of the archived text
2ac83dc3c71bffa78cbfa085edf6d550a92c946700127212aba77869f46396ee
Stable URL of this page
https://metraipolis.com/documento/dc_e16ad00bca95

How to cite

VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents — arXiv:2608.13831 — arXiv (en), https://arxiv.org/abs/2608.13831 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e16ad00bca95 (Metraipolis archive dc_e16ad00bca95, sha256 2ac83dc3c71bffa78cbfa085edf6d550a92c946700127212aba77869f46396ee)
BibTeX
@misc{dce16ad00bca95,
  title = {VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents — arXiv:2608.13831},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13831},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e16ad00bca95; sha256 2ac83dc3c71bffa78cbfa085edf6d550a92c946700127212aba77869f46396ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13831. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CL).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.13831 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:20:31.916Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).