LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

ACL ARR 2025 February Submission7374 Authors

Abstract:

Recent advancements in speech-to-speech dialogue systems leverage LLMs for multimodal interactions, yet they remain hindered by fine-tuning requirements, high computational overhead, and text-speech misalignment. Existing speech-enabled LLMs often degrade conversational quality by modifying the LLM, thereby compromising its linguistic capabilities.
In contrast, we propose LLMVoX, a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming TTS system that generates high-quality speech with low latency, while fully preserving the capabilities of the base LLM. Our approach achieves a significantly lower Word Error Rate compared to speech-enabled LLMs, while operating at comparable latency. Our approach achieves a significantly lower Word Error Rate than competing speech-enabled LLMs and delivers competitive speech quality with a high UTMOS score.
By decoupling speech synthesis from LLM processing via a multi-queue token streaming system, LLMVoX enables seamless, infinite-length dialogues. Its plug-and-play design also facilitates extension to various tasks with different backbones. Furthermore, LLMVoX generalizes to new languages with minimal dataset adaptation, attaining a low Character Error Rate on an Arabic speech task. Evaluations demonstrate that LLMVoX matches or surpasses existing speech-enabled LLMs in both speech quality and latency, while maintaining the original linguistic strengths of the LLM.
Additionally, we have integrated LLMVoX with a Vision-Language Model to create an omni-model with speech, text, and vision capabilities, without requiring additional multimodal training.

Paper Type: Long

Research Area: Speech Recognition, Text-to-Speech and Spoken Language Understanding

Research Area Keywords: speech technologies,spoken dialog,QA via spoken queries,spoken language understanding,Text-to-speech,Streaming Text-to-speech,AudioLLM.,

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English,Arabic

Submission Number: 7374