sherpa-onnx-tts

Convert plain text into speech using the offline sherpa-onnx runtime.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/kulharir7/karya --skill sherpa-onnx-tts-kulharir7
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/kulharir7/karya/tree/main/workspace/plugins/sherpa-onnx-tts
Command: npx skills add https://github.com/kulharir7/karya --skill sherpa-onnx-tts-kulharir7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Offline text-to-speech generation for on-device environments, eliminating cloud dependencies and preserving privacy.

Core Features & Use Cases

  • Local on-device TTS using sherpa-onnx runtime and voice models
  • Cross-platform support (macOS, Linux, Windows) with environment-based configuration
  • Use cases include accessibility, on-device narration, and offline demo playback

Quick Start

Generate an audio file from the text you provide using the local sherpa-onnx-tts tool.

Frequently Asked Questions about sherpa-onnx-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate speech from text without a cloud connection?

Generating speech from text without a cloud connection requires an on-device runtime like sherpa-onnx. This process transforms plain text into natural-sounding speech locally, ensuring privacy and functionality when network services are unavailable.

Does offline text-to-speech work on macOS, Linux, and Windows?

Yes, offline text-to-speech with sherpa-onnx supports cross-platform OS targets including macOS, Linux, and Windows. You configure the environment variables for the runtime and model directories to operate across these operating systems.

What environment variables do I need to set for sherpa-onnx text-to-speech?

To use sherpa-onnx text-to-speech, you must set the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables. These directories point the local runtime to the necessary execution files and voice models for generating audio.

When should I use on-device TTS instead of cloud-based services?

On-device TTS is ideal for offline voice assistants, accessibility tools, and on-device narration where cloud services are unavailable. It eliminates cloud dependencies and preserves user privacy by processing text locally without transmitting data.

Can I use local voice models for offline narration in restricted networks?

Yes, you can use local voice models for offline narration in restricted networks. By leveraging the sherpa-onnx runtime, the system processes text-to-speech entirely on-device, bypassing the need for external network access or cloud APIs.

Why is privacy important when choosing a text-to-speech solution?

Privacy is critical in text-to-speech solutions because cloud services transmit sensitive text data externally. Offline TTS with sherpa-onnx preserves privacy by generating audio locally on the device, ensuring no text leaves the local environment.