skills.rest
freire19
freire19COMMUNITY
Explore all skills by this author →
GitHub

sherpa-onnx-tts

Convert text to WAV audio offline using sherpa-onnx.

Updated May 8, 2026
Search Tags:#accessibility#sherpa-onnx#text to speech#offline tts#local audio generation#wav output
One-click install
npx skills add https://github.com/freire19/Mythos --skill sherpa-onnx-tts-freire19
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/freire19/Mythos/tree/main/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/freire19/Mythos --skill sherpa-onnx-tts-freire19

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the need for cloud-based text-to-speech by letting you convert text into audio entirely offline using local sherpa-onnx assets.

Core Features & Use Cases

  • Offline local TTS: Converts text to a WAV file using the sherpa-onnx offline CLI.
  • Configurable models: Selects voice/model files via environment variables (runtime + model directories, optional model file).
  • Repeatable setup: Downloads and unpacks the required runtime and a default English voice model into your state directory for consistent reuse.

Quick Start

Download the Skill runtime and a voice model, set SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR to the extracted paths, then run the wrapper to produce an output WAV file from your text prompt.

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 offline without cloud services?▼

Offline text-to-speech generation converts text into spoken audio files locally without contacting cloud services. This Skill uses the sherpa-onnx runtime and a voice model to render text prompts into WAV output on your machine.

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

To set up local text to speech, install the sherpa-onnx runtime and a TTS model. Set the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables to the extracted paths, optionally specifying SHERPA_ONNX_MODEL_FILE.

Can I use offline TTS for accessibility features and scripted announcements?▼

Yes, offline TTS supports accessibility features and scripted announcements. It applies to local voice synthesis for assistants and on-prem content production where local audio output is needed without external network connectivity.

Does offline text to speech require any external API dependencies?▼

No, offline text to speech requires no external API dependencies. The process downloads and unpacks the required runtime and a default English voice model into your state directory for consistent reuse without contacting cloud services.

What audio format is produced by local voice synthesis?▼

Local voice synthesis produces a WAV file as the output audio format. The wrapper renders your text prompt into this output WAV, making it usable for local assistants and accessibility features.

Related Skills

Explore More Content & Communication Skills→
mbaileymbailey
1.3k

voicemode

Manage local speech-to-text and text-to-speech services for voice conversations.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

TTS

Convert written text into spoken WAV, MP3, or PCM audio.

Community
Intermediate
bobmatnycbobmatnyc
3

langchain-framework

Build and orchestrate LLM-powered applications with LangChain.

Community
Intermediate
chebizarrochebizarro

sherpa-onnx-tts

Generate speech audio from text using sherpa-onnx with local voice models.

Community
Intermediate