LLMVoX
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM
About LLMVoX
Sambal Shikhar, Mohammed Irfan K, Sahal Shaji Mullappilly, Fahad Khan, Jean Lahoud, Rao Muhammad Anwer, Salman Khan, Hisham Cholakkal
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
LLMVoX is listed in this index written primarily in Python, with 313 stars on GitHub. Its latest recorded repository push was in May 2025; that is not an ASE editorial review date.
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118