sherpa-onnx-tts

Convert text input to speech using Sherpa-onnx offline.

23|10|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/deepgram/dglabs-deepclaw --skill sherpa-onnx-tts-deepgram
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/deepgram/dglabs-deepclaw/tree/main/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/deepgram/dglabs-deepclaw --skill sherpa-onnx-tts-deepgram

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts text to speech using the Sherpa-onnx library, eliminating the need for cloud-based services.

Core Features & Use Cases

  • Offline Operation: Perform text-to-speech conversion locally without internet access.
  • Voice Variety: Supports various voice models for different languages and accents.
  • Use Case: Create personalized voiceover for presentations, generate audio books, or add voice narration to videos.

Quick Start

Convert the text 'Hello from local TTS.' to speech and save it as '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 convert text to speech offline without relying on cloud services?

Offline text-to-speech can be performed locally using the Sherpa-onnx library, eliminating the need for cloud-based services or internet access during audio synthesis.

Does offline text-to-speech work on macOS, Linux, and Windows?

Yes, offline text-to-speech with Sherpa-onnx is compatible with macOS, Linux, and Windows, allowing local speech synthesis across these operating systems without cloud dependencies.

What do I need to generate speech locally with Sherpa-onnx?

To generate speech locally, you need the Sherpa-onnx runtime installed and a compatible voice model to process text input and synthesize audio output.

Can I use different languages and accents for offline voice generation?

Yes, offline voice generation supports various voice models, allowing you to generate speech in different languages and accents for personalized voiceovers, audiobooks, or video narration.

What is the best way to create local audio narration for videos and presentations?

Using offline text-to-speech with Sherpa-onnx provides a local method to create personalized voiceovers for presentations or add voice narration to videos without internet access.

How do I save my generated speech as an audio file like tts.wav?

You can convert text input to speech and save the output directly as an audio file, such as tts.wav, using the offline Sherpa-onnx text-to-speech process.