DataBubble·
Model Detail
Kokoro-82M
—Provider: hexgradCategory: audioPipeline: text-to-speech
DB Score
37.9
Downloads
11.6M
Likes
7K
Day
+0.0%
Week
+0.0%
Month
+0.0%
Overview
Kokoro-82M is an audio model released by hexgrad. The model is registered under the text-to-speech pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Technical
The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Use Cases
Kokoro-82M is best fit for speech recognition, transcription, or speech synthesis depending on the task head. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Download History
Research Paper
Model Info
Licenseapache-2.0
Citations291 (28 influential)
Recent newsView all news →