Overview
Kokoro is an open-weight text-to-speech model with only 82 million parameters, released under the Apache 2.0 license. Despite its small size, it gained attention in early 2025 for voice quality competitive with much larger systems, and for running fast enough for real-time use on modest hardware.
Highlights
- Only 82 million parameters
- Several voices and multiple languages
- Fast inference on CPUs and consumer GPUs
- Apache 2.0 license allowing commercial use
- Easy integration via Python packages
Typical uses
Local voice output for apps and assistants, audiobooks and accessibility tools where privacy or cost matters.
Things to consider
- Fewer voices and less expressive control than large commercial TTS services.
- No voice cloning.
- Language coverage is narrower than leading commercial services.
Specifications are taken from the provider’s official announcement, documentation or model card. Benchmark results depend on evaluation settings; see how AI benchmarks work.