Voice AI applications are gaining popularity as advances in large language models (LLMs) enable more natural and accessible spoken interactions. Serving these applications requires accounting not only for what users say, but also for how they speak (e.g., speaking rate) and the conditions under which their audio is captured and transmitted (e.g., background noise and packet loss). However, existing LLM systems represent conversation context as a flat, growing sequence of messages, leaving voice-specific context implicit in the audio. As a result, they can generate responses that are poorly aligned with user preferences, degrade interaction quality under adverse environmental conditions, and incur high costs over long voice sessions. We present llmovoice, a context-management middleware that explicitly models voice context and orchestrates its use. At each turn, llmovoice constructs a bounded voice context from the current user input, relevant interaction history, and explicit paralinguistic and environmental states. It then uses the serving LLM to reason over this context and generate runtime directives that guide how the system responds. We evaluate llmovoice on real-world voice applications and benchmarks. It reduces speaking-rate alignment error by 52.4%, lowers the false-interruption rate from 46.0% to 0.9% under packet loss, and reduces model usage cost by 79.2%. For long sessions, llmovoice reduces per-turn cost by up to 24.9 times while retaining up to 98.7% of baseline answer quality.
Figures & tables
Figure 1. Overview of the LLM-over-voice serving pipeline.
Figure 2
Figure 4. System overview of llmovoice .
Figure 5. Context orchestrator maps the current states and runtime configuration to validated runtime directives.
Figure 6. Memory layout and context-window construction. The context projector uses vthreads and vpages to construct projected history under a context budget, selecting among audio, transcript, and summary representations.
Policy
FIR
Latency (ms)
Network cost ($/trace)
Fixed-500
46.0%
1286.1
0.003344
Static-Max
0.0%
4021.4
0
llmovoice
0.9%
1830.7
0.000695
Table 1. Turn-control results over ICASSP PLC traces.
Figure 7. Cost per turn versus conversation history length.
LLM-based full-duplex voice services allow users to speak while the assistant is responding. Because servers can generate output and advance dialogue state faster than clients can play it, subsequent user speech may be interpreted based on content the user never heard. We call this failure Generative Context Mis-anchoring (GCM). To address GCM issues, we present PACE, a provider-independent middleware layer that anchors model-facing context to the client playback boundary, a system-observable proxy for what the user could have heard. After an interruption, PACE repairs this context to exclude assistant content that never reached playback, while preserving low-latency generation across heterogeneous voice runtimes. We implement PACE's audio-only projection path end to end in a browser-based realtime voice assistant using a black-box speech model, without modifying the model service. We also construct GCM-Bench, a new controlled benchmark dataset of 108 playback-relative referent-anchoring cases. On GCM-Bench, PACE raises Referent Anchoring Accuracy from 25.0% to 96.3% over a cancellation-only baseline. On 200 Full-Duplex-Bench v1 interruption samples, it preserves interruption response quality. These results show that grounding model-facing context in actual playback is a practical way to maintain consistency in full-duplex voice dialogue.
Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While many agentic pipelines mitigate this by resetting state at each turn, this approach discards vital context and impairs performance at turn onsets. We propose two state-management strategies that preserve cross-utterance context to reduce onset errors. In experiments with two state-of-the-art streaming models on two spoken dialogue benchmarks, our best method yields an average of 15-21% relative WER reduction at utterance onsets.
Sameep Chattopadhyay, Alexander Erdmann, Mari Ostendorf
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.
Edresson Casanova, Jaehyeon Kim, Mariana Graterol Fuenmayor +17