CPU-only TTS that runs on Raspberry Pi. The best quality-per-watt ratio of any voice model — 82M parameters producing studio-quality speech synthesis. Apache 2.0 commercial license with no GPU requirement whatsoever.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 2GB VRAM Recommended
The Kokoro-82M model by hexgrad is a 82M parameter architecture optimized for audio tasks. It requires approximately 0GB of VRAM to comfortably run locally using a CPU quantization. Extending the context window up to 0 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running Kokoro-82M at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 2GB of VRAM to run the CPU quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run kokoro' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.