Sherpa-ONNX Voice Models

This repository is a mirror hosting lightweight models for use with the Sherpa-ONNX framework. Models are compressed into archives for easy single-request downloading.

Attribution & Licensing

These models are mirrored from the original creators to ensure stable downloads for our application.

Licensing by Directory

  • /models/stt/: Licensed under CC BY-SA 4.0.
    • Original author: Banafo / Kroko-ASR.
  • /models/tts/: Licensed under the OpenRAIL-M License.
    • Model: Supertone/supertonic-3 (int8 format, sourced via Sherpa-ONNX).
    • Copyright (c) 2026 Supertone Inc.
    • Note: The OpenRAIL-M license includes specific use-based restrictions. Please see the original repository for details.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support