---
id: sherpa-onnx-core
version: "1.13.5"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# sherpa-onnx-core — Core shared libraries for sherpa-onnx

License: permissive · Maintenance: active · Downloads: 526.4K/mo

## What it is and what it does

sherpa-onnx-core is a Python wrapper around pre-compiled ONNX runtime binaries for running speech and audio AI models locally. It bundles the core C++ libraries needed to execute speech recognition (streaming and non-streaming), text-to-speech, speaker diarization, voice activity detection, keyword spotting, audio tagging, and speech enhancement—all without external service dependencies.

The package targets embedded and edge devices as well as desktop environments, supporting x86, ARM (32 and 64-bit), RISC-V, and specialized NPUs (Rockchip, Qualcomm, Ascend). It has no Python runtime dependencies, only platform-specific binary wheels, making it lightweight for deployment. Users typically pair it with pre-trained ONNX models from the sherpa-onnx ecosystem to perform inference.

Use it for:

- Build offline speech-to-text applications on mobile, embedded Linux, or desktop without cloud API calls
- Implement real-time voice activity detection and keyword spotting for always-on voice interfaces
- Deploy speaker identification or diarization in privacy-sensitive environments where audio cannot leave the device
- Add text-to-speech synthesis to applications running on Raspberry Pi, Jetson, or other edge hardware
- Integrate speech enhancement or source separation into audio processing pipelines on resource-constrained devices

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

sherpa-onnx-core provides pre-built ONNX runtime binaries for speech recognition, synthesis, speaker identification, audio tagging, and other audio processing tasks across multiple platforms and architectures.

Yes, if you need local, offline speech or audio AI inference. The package is actively maintained, has no Python dependencies, supports a wide range of platforms and architectures, and carries a permissive license. Install friction is moderate due to platform-specific wheels, but pre-built binaries eliminate the need to compile ONNX Runtime yourself. Verify that your target platform is in the supported list before committing.

## Install

pip install sherpa-onnx-core
uv add sherpa-onnx-core
poetry add sherpa-onnx-core

## Installing sherpa-onnx-core

Before you install: Medium install friction due to platform-specific wheels (9 variants covering macOS, Linux, Windows, and ARM architectures). Active maintenance with recent releases (3 days since last version); repository shows strong community engagement with 14181 stars.

License in practice: Licensed under Apache-2.0 (permissive), allowing free use, modification, and distribution with minimal restrictions—suitable for both open-source and commercial projects.

Quickstart:

pip install sherpa-onnx-core

import sherpa_onnx
# Use sherpa_onnx APIs for speech recognition, TTS, or other audio tasks

Requires a compatible platform wheel; installation may fail on unsupported architectures (e.g., 32-bit x86 on macOS, or RISC-V on Windows).

Verify before relying:

- Whether Python version constraints exist beyond what the fact sheet specifies
- Whether pre-trained models are bundled or must be downloaded separately
- Performance characteristics and latency on different hardware targets

## Package facts

- License: Apache-2.0 (permissive)
- Python support: unspecified
- Install friction: medium
- Maintenance: active
- Downloads: 526.4K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

speech recognition library, text to speech offline, speaker identification, audio processing onnx, voice activity detection, keyword spotting, speech enhancement, speech-processing, edge-inference, offline-ai

[View on SkillFed](https://skillfed.io/packages/sherpa-onnx-core) · [View on PyPI](https://pypi.org/project/sherpa-onnx-core/)