sherpa-onnx-tts

Generates audio files from text using local sherpa-onnx engine.

5.1k|1.2k|Updated Feb 23, 2026

Search Tags:#offline #text-to-speech #local #tts #voice generation #sherpa-onnx

Ready to run

npx skills add https://github.com/linuxhsj/openclaw-zero-token --skill sherpa-onnx-tts-linuxhsj

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill provides a completely offline, local text-to-speech (TTS) solution, eliminating the need for internet connectivity or cloud-based services for voice generation.

Core Features & Use Cases

Local TTS Engine: Utilizes the sherpa-onnx library for high-quality speech synthesis directly on your machine.
Offline Operation: Works without any internet connection, ensuring privacy and availability.
Multiple Voices: Supports various voice models, allowing you to choose different speech styles.
Use Case: Generate audio files for presentations, accessibility tools, or personal projects without relying on external APIs or incurring costs.

Quick Start

Use the sherpa-onnx-tts skill to convert the text "Hello from local TTS." into an audio file named tts.wav.

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 offline using a local TTS engine?▼

You can generate speech from text offline using a local TTS engine by running the sherpa-onnx synthesis process directly on your machine, which outputs an audio file like tts.wav without requiring internet connectivity.

What environment variables do I need to set for local text-to-speech generation?▼

To perform local text-to-speech generation, you must set the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables so the engine can locate its runtime files and voice models for audio synthesis.

Can I use different voice models for offline voice generation?▼

Yes, offline voice generation supports various voice models, allowing you to choose different speech styles and configurations for generating audio files directly through the sherpa-onnx engine.

What is the best way to convert text to speech locally without cloud APIs?▼

The best way to convert text to speech locally without cloud APIs is using an offline solution like sherpa-onnx, which ensures privacy and availability by synthesizing high-quality speech directly on your machine.

Does offline text-to-speech work without an internet connection?▼

Yes, offline text-to-speech works completely without an internet connection, eliminating the need for cloud-based services and ensuring privacy while generating audio files locally on your machine.

What are the limitations of using a local TTS engine for voice synthesis?▼

A limitation of using a local TTS engine for voice synthesis is the prerequisite environment setup, requiring specific local directories for the runtime and model files to be configured before generating any audio.