{"repo":"mbzuai-oryx/LLMVoX","free":true,"listed":false,"github":"https://github.com/mbzuai-oryx/LLMVoX","clone":"git clone https://github.com/mbzuai-oryx/LLMVoX.git","description":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","language":"Python","stars":309,"topics":["audiollm","mbzuai","neural-speech-synthesis","streaming","text-to-speech","transformers","tts","voice-assistant","wavtokenizer","llmvox"],"license":null,"category":"machine-learning","readme_excerpt":"Accepted at ACL 2025 Findings 🏅 LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM Sambal Shikhar , Mohammed Irfan K , Sahal Shaji Mullappilly , Fahad Khan , Jean Lahoud , Rao Muhammad Anwer , Salman Khan , Hisham Cholakkal Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), UAE Overview LLMVoX is a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming Text-to-Speech (TTS) system designed to convert text outputs from Large Language Models into high-fidelity streaming speech with low latency. Our approach achieves significantly lower Word Error Rate compared to speech-enabled LLMs while operating at comparable latency and speech quality. Key features: - 🚀 Lightweight & Fast : Only 30M parameters, delivering speech with end-to-end latency as low as 300ms - 🔌 LLM-Agnostic : Just plug with any existing LLM and Vision-Language Models without requiring fine-tuning or architectural modifications. - 🌊 Multi-Queue Streaming : Enables continuous, low-latency speech generation and infinite-length dialogues - 🌐 Multilingual Support : Easily adaptable to new languages with only dataset adaptation Requirements Quick Start Download Required Checkpoints Download the necessary model checkpoints from Hugging Face: 🤗 Hugging Face Repository : MBZUAI/LLMVoX Configuration Basics LLMVoX requires a few base paths to be set correctly in the inference configuration file at configs/inference config.py : wavtokenizer model path : Path to the pretrained Wav","default_branch":null,"files":null,"tree":[],"storefront":"/r/mbzuai-oryx","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/mbzuai-oryx/LLMVoX/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}