sherpa-onnx-tts

Name: sherpa-onnx-tts
Availability: InStock
Author: liutao96

Generate speech audio from text offline using sherpa-onnx.

Updated Feb 14, 2026

Search Tags:#runtime #offline #text-to-speech #tts #multiplatform #wrapper #sherpa-onnx

Ready to run

npx skills add https://github.com/liutao96/skill --skill sherpa-onnx-tts-liutao96

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/liutao96/skill/tree/main/sherpa-onnx-tts
Command: npx skills add https://github.com/liutao96/skill --skill sherpa-onnx-tts-liutao96

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local text-to-speech generation often relies on cloud services or proprietary engines, leading to latency, privacy concerns, and internet dependency. This skill provides an offline, local TTS pipeline powered by sherpa-onnx that runs without network access.

Core Features & Use Cases

Offline TTS synthesis using the sherpa-onnx runtime and compatible voice models.
Cross-platform support (macOS, Linux, Windows) with a simple wrapper to generate speech audio from text.
Environment-based configuration using SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR for deterministic deployments.

Quick Start

Install the sherpa-onnx runtime and a voice model, then run the wrapper to synthesize speech from text.

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 audio from text offline without a cloud service?▼

Offline text-to-speech synthesis generates speech audio locally without network access. This skill uses the sherpa-onnx runtime and compatible voice models to convert text into speech on your machine, eliminating cloud latency and internet dependency.

What environment variables do I need to configure for offline text-to-speech?▼

Offline text-to-speech requires configuring SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables. These point to the sherpa-onnx runtime and voice model directories, enabling deterministic deployments and consistent speech synthesis execution.

Does offline TTS work on macOS, Linux, and Windows development workflows?▼

Offline TTS supports cross-platform development workflows across macOS, Linux, and Windows. The skill provides a simple wrapper binary that executes the sherpa-onnx runtime to synthesize speech from text on all three operating systems.

Why use local text-to-speech generation instead of cloud-based TTS APIs?▼

Local text-to-speech generation avoids the latency, privacy concerns, and internet dependency of cloud-based TTS APIs. Running sherpa-onnx locally ensures privacy-preserving speech synthesis for applications, assistants, and accessibility features without transmitting text data externally.

What do I need to install before running an offline text-to-speech pipeline?▼

Running an offline text-to-speech pipeline requires installing the sherpa-onnx runtime and a compatible voice model. You must also set the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables before executing the provided wrapper binary.

Can I use offline TTS for accessibility features in my applications?▼

Offline TTS is suitable for accessibility features in applications, assistants, and other software. The sherpa-onnx pipeline generates speech audio from text locally, providing privacy-preserving voice output without requiring cloud connectivity or external API calls.