sherpa-onnx-tts

Generate speech audio files locally with sherpa-onnx and Node.js.

19.0k|5.6k|Updated Jul 9, 2024
One-click install
npx skills add https://github.com/elizaOS/eliza --skill sherpa-onnx-tts-elizaos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/elizaOS/eliza/tree/main/packages/skills/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/elizaOS/eliza --skill sherpa-onnx-tts-elizaos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables local, offline text-to-speech generation using the sherpa-onnx framework, eliminating the need for an internet connection and cloud services.

Core Features & Use Cases

  • Local TTS Generation: Convert text into speech audio files directly on your machine.
  • Offline Capability: Operates entirely without an internet connection, ensuring privacy and availability.
  • Customizable Voices: Supports various voice models for different speech outputs.
  • Use Case: Generate spoken audio for documentation, accessibility features, or voice assistant responses without relying on external APIs.

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 audio offline without using cloud APIs?

You can generate speech audio offline by running local text-to-speech synthesis through the sherpa-onnx runtime, which converts text into audio files directly on your machine without needing an internet connection.

Can I use local TTS generation with custom voice models on my operating system?

Yes, local TTS generation supports various custom voice models across different operating systems by executing a Node.js wrapper script that interfaces with the sherpa-onnx CLI.

What environment variables do I need to set for offline text-to-speech synthesis?

Offline text-to-speech synthesis requires specific environment variables for the runtime and model directories so the Node.js wrapper script can correctly locate and load the necessary sherpa-onnx components.

What's the best way to convert text into a WAV file locally for accessibility features?

The best way to convert text into a WAV file locally is using offline TTS generation, which outputs audio files like tts.wav directly on your machine, ensuring privacy and availability for accessibility features.

Does local text-to-speech work entirely without an internet connection?

Yes, local text-to-speech operates entirely without an internet connection, eliminating the need for cloud services and ensuring complete privacy during audio generation.