VoxCPM

### TL;DR

VoxCPM is an open-source, tokenizer-free text-to-speech (TTS) engine designed for context-aware speech generation and true-to-life voice cloning. It utilizes hierarchical language modeling to synthesize high-quality continuous speech representations directly from input text, supporting real-time streaming output of generated audio segments.

Key Insights & Metrics

Key Features

• Tokenizer-free end-to-end architecture
• Zero-shot voice cloning with 3-10 seconds of reference audio
• High efficiency with real-time inference on consumer GPUs
• Context-aware speech generation with intonation style inference
• Cross-language synthesis between Chinese and English

Discussion