skills.rest
adoresever
adoreseverCOMMUNITY
Explore all skills by this author →
GitHub

sherpa-onnx-tts

Generate speech locally from text using sherpa-onnx.

202|36|Updated Jan 27, 2026
Search Tags:#runtime#offline#text-to-speech#tts#sherpa-onnx#voice-model
One-click install
npx skills add https://github.com/adoresever/AGI_Ananas --skill sherpa-onnx-tts-adoresever
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/adoresever/AGI_Ananas/tree/main/26.2.21openclaw-viking/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/adoresever/AGI_Ananas --skill sherpa-onnx-tts-adoresever

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local, privacy-preserving text-to-speech generation without cloud services.

Core Features & Use Cases

  • Offline TTS: generate speech locally without internet connectivity.
  • Cross-platform: works on macOS, Linux, and Windows with downloadable runtimes and voices.
  • Simple integration: configure SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR to enable usage.

Quick Start

Download the runtime for your OS and a voice model, set the environment variables SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR, then run the wrapper to synthesize speech from text.

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 text-to-speech generation locally without an internet connection?▼

Offline text-to-speech generation runs locally by using sherpa-onnx to synthesize speech from text without cloud services. It requires downloading the runtime and a voice model, then configuring environment variables to enable privacy-preserving audio output on your machine.

What do I need to configure to set up offline TTS with sherpa-onnx on my machine?▼

To set up offline TTS, you must download the sherpa-onnx runtime and a voice model, then configure the SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables. This allows the wrapper to locate resources and synthesize speech locally.

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

Offline text-to-speech generation works cross-platform on macOS, Linux, and Windows. You must download the specific runtime built for your operating system and configure the model directory environment variable to produce speech locally.

Why use offline TTS instead of cloud-based text-to-speech services?▼

Use offline TTS for local, privacy-preserving text-to-speech generation without cloud services. It ensures no internet connectivity is required and protects data privacy, making it suitable for sensitive voice assistants, content narration, and accessibility tools.

Can I use local text-to-speech generation for voice assistants and accessibility tools?▼

Local text-to-speech generation is applicable for voice assistants, content narration, and accessibility tools. By running sherpa-onnx on your machine, you can synthesize speech from text offline to provide immediate, privacy-preserving auditory output.

Related Skills

Explore More Software Engineering Skills→
jason9693jason9693

sherpa-onnx-tts

Synthesize speech from text offline using sherpa-onnx and Piper models.

Community
Intermediate
NJX-njxNJX-njx
55

sag

Convert input text into natural speech audio using ElevenLabs APIs.

Community
Basic
kaivyykaivyy
20

Voice Skill

Transcribe audio files with OpenAI Whisper and synthesize speech from text.

Community
Intermediate
liutao96liutao96

sherpa-onnx-tts

Generate speech audio from text offline using sherpa-onnx.

Community
Advanced