hexgradJan 27, 2025
Kokoro-82M
A tiny 82-million-parameter open text-to-speech model with natural-sounding voices, small enough to run quickly on ordinary hardware.
- Type
- Speech
- Context
- —
- Weights
- Open
Tag
Every The Latent Daily story, tool, model and resource tagged “Speech Models”.
A tiny 82-million-parameter open text-to-speech model with natural-sounding voices, small enough to run quickly on ordinary hardware.
OpenAI's open-source speech recognition model for transcription and translation into English across dozens of languages.