Downloads · 30 days
0
kokoro-82M-endpoint
jrmeyer-veris/kokoro-82M-endpoint
kokoro-82M-endpoint is a text-to-speech model from jrmeyer-veris. Use it when you need text read aloud. The card lists the license as apache-2.0.
Serves hexgrad/Kokoro-82M on a dedicated Hugging Face Inference Endpoint via a custom handler.py.
Access
Public
Updated Aug 6, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 41%
At a glance
- Task
- Text-to-Speech
- License
- apache-2.0
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026
- SHA
- e609f830
Model card
From the Hugging Face model README
Kokoro-82M Inference Endpoints handler
Serves hexgrad/Kokoro-82M on a
dedicated Hugging Face Inference Endpoint via a custom handler.py.
Request
{"inputs": "Text to speak.", "parameters": {"voice": "af_heart", "speed": 1.0}}
voice is a Kokoro voice id (af_*/am_* are American female/male).
Response
{"audio_b64": "<base64 WAV, 24 kHz mono s16>", "sample_rate": 24000}
Deploy: the model is 82M params — an Nvidia L4 is ample; CPU works too.
First boot installs requirements.txt and downloads the ~330 MB model.
- Task
- Text-to-Speech
- License
- apache-2.0
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026