# VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents

arXiv: https://arxiv.org/abs/2608.13831 · HTML: https://mlsanity.com/paper/2608.13831/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 20 of 20)

- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://mlsanity.com/paper/2508.14444/) (2025)
- [PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models](https://mlsanity.com/paper/2602.06053/) (2026)
- [TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context](https://mlsanity.com/paper/2110.04410/) (2021)
- [Hi-Fi Multi-Speaker English TTS Dataset](https://mlsanity.com/paper/2104.01497/) (2021)
- [TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio](https://mlsanity.com/paper/2304.01448/) (2023)
- [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations](https://mlsanity.com/paper/2304.06795/) (2023)
- [Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models](https://mlsanity.com/paper/2507.23159/) (2025)
- [SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model](https://mlsanity.com/paper/2505.15670/) (2025)
- [Lhotse: a speech data representation library for the modern deep learning ecosystem](https://mlsanity.com/paper/2110.12561/) (2021)
- [Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance](https://mlsanity.com/paper/2502.05236/) (2025)
- [HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset](https://mlsanity.com/paper/2506.04152/) (2025)
- [SpeakStream: Streaming Text-to-Speech with Interleaved Data](https://mlsanity.com/paper/2505.19206/) (2025)
- [Efficient Generative Modeling with Residual Vector Quantization-Based Tokens](https://mlsanity.com/paper/2412.10208/) (2024)
- [DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities](https://mlsanity.com/paper/2502.11123/) (2025)
- [VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency](https://mlsanity.com/paper/2509.15969/) (2025)

## Built on by (most cited first, 3 of 3)

- [A frontend-backend architecture for tool calls in full-duplex speech models](https://mlsanity.com/paper/2609.19334/) (2026)
- [Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models](https://mlsanity.com/paper/2609.15759/) (2026)
- [Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes](https://mlsanity.com/paper/2609.30798/) (2026)

## Abstract (arXiv)

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.