KittenML/KittenTTS

Text-to-speech model under 25MB

View on index · View in 3D Map

Related repos

• self-hosted lightweight text-to-speech server with web UI and GPU support
• human-level text-to-speech using style diffusion and large speech models
• multi-lingual text-to-speech that runs fast on CPUs
• zero-shot text-to-speech with voice cloning for English and Chinese
• open-weight text-to-speech model for fast, natural voice synthesis
• open source text-to-speech model built by inverting Whisper, supports voice cloning and multilingual output
• Optimized speech-to-text pipeline for Whisper
• open-source text-to-speech with voice cloning and emotion control
• fast local text-to-speech using llama.cpp, works on CPU