skills.rest
nomad3
nomad3COMMUNITY
Explore all skills by this author →
GitHub

sherpa-onnx-tts

Generates offline speech audio from input text to WAV using sherpa-onnx CLI tools.

Updated Feb 8, 2026
Search Tags:#text-to-speech#local cli#sherpa-onnx#offline tts#wav generation#voice model#node wrapper
One-click install
npx skills add https://github.com/nomad3/openclaw-k8s --skill sherpa-onnx-tts-nomad3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/nomad3/openclaw-k8s/tree/main/package/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/nomad3/openclaw-k8s --skill sherpa-onnx-tts-nomad3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill solves the problem of generating speech audio from text without relying on cloud services.

Core Features & Use Cases

  • Offline CLI-based local TTS: Produces a WAV file using sherpa-onnx’s offline TTS binary.
  • Model and runtime setup: Guides downloading the correct sherpa-onnx runtime per OS and a selectable voice model for consistent results.
  • Flexible inputs and overrides: Supports selecting a specific model file, tokens file, and espeak-ng data directory either via environment variables or command-line flags.

Use case: You need short voice prompts for a local kiosk or assistant and want predictable offline synthesis with a known voice.

Quick Start

Download the sherpa-onnx runtime and the Lessac high voice model, then run the skill wrapper to synthesize your speech into a 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 from text offline?▼

Offline text-to-speech synthesis works by using local binaries and voice model assets to process input text and generate a WAV file, requiring no internet connection or cloud API calls.

What do I need to set up before running local text-to-speech synthesis?▼

Local text-to-speech synthesis requires downloading the sherpa-onnx runtime for your operating system and a voice model, then setting the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables to resolve necessary files.

Can I generate voice prompts for a local kiosk without an internet connection?▼

Yes, generating voice prompts for a local kiosk without an internet connection is supported by using the offline TTS binary with a known voice model to produce predictable, deterministic audio output.

How do I specify a custom voice model or tokens file for offline TTS?▼

You can specify a custom voice model, tokens file, or espeak-ng data directory for offline TTS by passing command-line flags or setting corresponding environment variables before invoking the wrapper.

Does offline text-to-speech work across different operating systems?▼

Offline text-to-speech works across different operating systems by downloading the correct sherpa-onnx runtime per OS and setting the appropriate dynamic library environment before invoking the synthesis binary.

Related Skills

Explore More Software Engineering Skills→
vut08905vut08905

sherpa-onnx-tts

Convert text to speech using an offline sherpa-onnx TTS engine.

Community
Intermediate
kcns008kcns008
5

sherpa-onnx-tts

Generates offline text-to-speech audio from plain text using sherpa-onnx runtime and voice models.

Community
Intermediate
PolealphaPolealpha

sherpa-onnx-tts

Generate offline speech audio as WAV files using sherpa-onnx TTS.

Community
Intermediate
nuno7lopesnuno7lopes

sherpa-onnx-tts

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

Community
Basic