skills.rest
SafeAI-Lab-X
SafeAI-Lab-XCOMMUNITY
Explore all skills by this author →
GitHub

sherpa-onnx-tts

Synthesize offline speech with sherpa-onnx runtimes and models.

1.0k|59|Updated Mar 20, 2026
Search Tags:#runtime#offline#model#local#tts#speech#sherpa-onnx
One-click install
npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill sherpa-onnx-tts-safeai-lab-x
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill sherpa-onnx-tts-safeai-lab-x

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local, offline text-to-speech synthesis using sherpa-onnx without requiring cloud services.

Core Features & Use Cases

  • Offline, on-device TTS: Generate natural-sounding speech without internet.
  • OS-wide availability: Supports macOS, Linux, and Windows runtimes with platform-specific downloads.
  • Use Case: Build an offline voice assistant or accessible UI with locally synthesized speech.

Quick Start

Download the sherpa-onnx runtime for your OS, download a voice model, configure SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR, and run the provided wrapper to generate speech.

Frequently Asked Questions about sherpa-onnx-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run offline text-to-speech synthesis locally without cloud services?▼

Offline text-to-speech synthesis is achieved by downloading the sherpa-onnx runtime and a voice model, configuring local environment variables, and using a wrapper binary to generate speech without internet.

Can I use offline TTS on macOS, Linux, and Windows environments?▼

Yes, offline TTS supports macOS, Linux, and Windows environments by downloading platform-specific runtimes and configuring the respective environment variables for local speech synthesis.

What environment variables do I need to set up for local TTS model configuration?▼

Local TTS model configuration requires setting SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables to point to the downloaded platform-specific runtime and voice model directories.

Do I need an internet connection to generate natural-sounding speech with sherpa-onnx?▼

No, an internet connection is not needed to generate natural-sounding speech because sherpa-onnx operates entirely on-device using downloaded local runtimes and voice models.

When should I use offline TTS for building a voice assistant or accessible UI?▼

Use offline TTS when building a voice assistant or accessible UI that requires locally synthesized speech without cloud dependencies, ensuring privacy and operation in disconnected environments.

What are the steps to download and configure runtimes for on-device speech synthesis?▼

Download the platform-specific sherpa-onnx runtime for your OS, download a voice model, set SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR, and run the provided wrapper to synthesize speech.

Related Skills

Explore More Software Engineering Skills→
WarrenZhu050413WarrenZhu050413
7

generating-tts

Generate and play multilingual text-to-speech audio with adjustable voices and speeds.

Community
Intermediate
X-School-AcademyX-School-Academy
19

live-tts-text-to-audio

Convert input text into audible speech via a live text-to-speech engine.

Official
Basic
Yapie0Yapie0
55

sag

Generate local text-to-speech audio using the sag CLI with ElevenLabs TTS.

Community
Intermediate
nuno7lopesnuno7lopes

sherpa-onnx-tts

Convert text to speech offline using sherpa-onnx with various voice models.

Community
Basic