openbmb/VoxCPM2
Text-to-Speech β’ Updated β’ 12.8k β’ 923
Speech generation from text and acoustic reference
Chat with AI using custom language models
Zero GPU Text-to-Speech using Fish Audio S2 Pro
Real-time voice cloning entirely in your browser! (CPU)
Generate HTML templates using Jinja
Transcribe audio recordings into written text
Visualize embeddings in 3D space, powered by EmbeddingGemma
State-of-the-art TTS model under 25MB
In a way I wonder if thereβs a connection to the latest elevenlabs release one day after π€π€