sherpa-onnx-tts

Generate speech audio locally using sherpa-onnx runtime and voice models.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/lehalpaul/agents --skill sherpa-onnx-tts-lehalpaul
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/lehalpaul/agents/tree/main/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/lehalpaul/agents --skill sherpa-onnx-tts-lehalpaul

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

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

Core Features & Use Cases

  • Local TTS: Generates speech audio directly on your machine using the sherpa-onnx library.
  • Offline Operation: Functions entirely without an internet connection, ensuring privacy and availability.
  • Customizable Voices: Supports downloading and using various voice models for different speech outputs.
  • Use Case: Convert meeting notes or generated text into spoken audio for later review or accessibility, all without sending data to external servers.

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 locally without an internet connection?

Local text-to-speech generation works by using the sherpa-onnx runtime to synthesize text into audio files directly on your machine. This offline approach eliminates internet dependency and ensures data privacy by keeping all processing on-device.

What do I need to set up offline text-to-speech with sherpa-onnx?

To set up offline text-to-speech with sherpa-onnx, you need the sherpa-onnx runtime binaries and pre-downloaded TTS voice model files present on your local machine. These components are required to execute on-device audio synthesis without a network connection.

Can I use custom voice models for local TTS generation?

Yes, you can use custom voice models for local TTS generation by downloading and integrating various voice models with the sherpa-onnx runtime. This allows you to customize the speech output to suit different applications and accessibility requirements.

Does offline text-to-speech work for converting meeting notes into spoken audio?

Offline text-to-speech works for converting meeting notes into spoken audio by processing the text locally through the sherpa-onnx runtime and outputting a synthesized audio file. This is ideal for later review or accessibility without sending sensitive meeting data to external servers.

What are the limitations of local voice generation compared to cloud-based TTS?

Local voice generation requires you to manually manage sherpa-onnx runtime binaries and pre-download voice model files. You need sufficient local storage and compute resources to handle the on-device audio synthesis without relying on cloud-based infrastructure.