Kale TTS 1 Base
Adapts Kokoro-82M to ten designed voices, tuning the text and prosody components while retaining the original sound decoder.
Specifications
- Released
- Nov 19, 2026
- Inputs
- Text
- Weights
- Open weights · Apache-2.0
- Task
- Speech synthesis
- Published capabilities
- Adapts Kokoro-82M to ten designed voices, tuning the text and prosody components while retaining the original sound decoder.
- Access
- Downloadable publisher checkpoint
- Result
- Synthesized speech
- Sources
- Model weights