sherpa-onnx-tts

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

1|Updated Mar 8, 2026

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

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a local, offline text-to-speech (TTS) solution, eliminating the need for cloud-based services and ensuring privacy and accessibility.

Core Features & Use Cases

Local TTS: Generates speech directly on your machine without internet connectivity.
Privacy-Focused: Keeps your audio data local, ideal for sensitive applications.
Customizable Voices: Supports various voice models for different speech outputs.
Use Case: Convert meeting notes or generated reports into audio files for later listening without relying on external APIs.

Quick Start

Use the sherpa-onnx-tts skill to convert the phrase "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 without internet connectivity?▼

Offline text-to-speech synthesis generates speech audio directly on your local machine. It uses the sherpa-onnx runtime with Piper voice models to convert text into audio files without relying on cloud-based APIs.

What environment variables do I need for local voice synthesis?▼

Local voice synthesis requires SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables to be set. These point the sherpa-onnx runtime to the necessary execution libraries and Piper voice models for audio generation.

Can I use offline text-to-speech for sensitive applications requiring privacy?▼

Offline text-to-speech is ideal for privacy-focused applications. It keeps all audio data and text processing local on your device, eliminating the risk of exposing sensitive information to external cloud services.

Does sherpa-onnx text-to-speech support customizable voice models?▼

Sherpa-onnx text-to-speech supports customizable voices through various Piper voice models. You can swap voice models to achieve different speech outputs by configuring the SHERPA_ONNX_MODEL_DIR environment variable.

How do I convert meeting notes into an audio file using local TTS?▼

Local TTS converts text like meeting notes into audio files by processing the text through the sherpa-onnx runtime. It outputs a local audio file, such as a wav file, for later listening without internet connectivity.

What is the best way to run text-to-speech without cloud APIs?▼

The best way to run text-to-speech without cloud APIs is using a local runtime like sherpa-onnx with Piper voice models. This approach ensures on-device audio generation, maintaining privacy and operating without internet connectivity.