skills.rest
kelinfoxy
kelinfoxyCOMMUNITY
Explore all skills by this author →
GitHub

sherpa-onnx-tts

Convert text to speech locally using sherpa-onnx with downloaded runtimes and models.

1|1|Updated Jan 22, 2026
Search Tags:#runtime#offline#local#tts#wrapper#onnx#sherpa-onnx
One-click install
npx skills add https://github.com/kelinfoxy/EZ-Homelab --skill sherpa-onnx-tts-kelinfoxy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sherpa-onnx-tts
Source: https://github.com/kelinfoxy/EZ-Homelab/tree/main/docker-compose/ez-assistant/skills/sherpa-onnx-tts
Command: npx skills add https://github.com/kelinfoxy/EZ-Homelab --skill sherpa-onnx-tts-kelinfoxy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local text-to-speech via sherpa-onnx enables offline TTS without cloud services, preserving privacy and reducing latency.

Core Features & Use Cases

  • Offline TTS: Synthesize speech locally on supported platforms (macOS, Linux, Windows) without internet access.
  • Cross-platform compatibility: Works with pre-downloaded runtimes and models managed through the skill.
  • Use case: Add spoken announcements in kiosks, accessibility narration, or embedded devices where cloud TTS is unavailable.

Quick Start

Download the sherpa-onnx runtime and a voice model, set 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 offline text-to-speech locally without cloud dependency?▼

Offline text-to-speech synthesis runs locally using sherpa-onnx, removing cloud dependency by generating speech directly on your device. This preserves privacy and reduces latency for announcements and accessibility narration.

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

Local TTS requires setting SHERPA_ONNX_RUNTIME_DIR and SHERPA_ONNX_MODEL_DIR environment variables. You must also download the sherpa-onnx runtime, a voice model, and the wrapper binary to execute speech synthesis.

Can I use offline TTS on embedded devices and servers?▼

Offline TTS works across desktops, servers, and embedded devices using pre-downloaded runtimes and models. It supports macOS, Linux, and Windows platforms for private announcements where cloud services are unavailable.

What's the best way to synthesize speech for accessibility narration without internet?▼

Synthesizing speech for accessibility narration without internet is best handled by local offline TTS using sherpa-onnx. Download a compatible voice model, configure the environment variables, and run the wrapper to generate audio.

Why does local TTS need a downloaded runtime and voice model?▼

Local TTS needs a downloaded runtime and voice model because it operates entirely offline without cloud processing. The runtime provides execution infrastructure while the model contains the acoustic data required to synthesize speech.

When should I not use offline text-to-speech?▼

You should not use offline text-to-speech if you lack the storage for local voice models or need continuous internet-independent updates. It requires pre-downloading runtimes and models, making it less dynamic than cloud TTS.

Related Skills

Explore More Software Engineering Skills→
gizixgizix
2

model-deployment

Package trained machine learning models with versioning, ONNX export, and FastAPI endpoints.

Community
Advanced
team-telnyxteam-telnyx
3

telnyx-voice-media-go

Manage Teleinx voice media streams in Go with SDK examples for playback, recording, and speech synthesis.

Official
Intermediate
rahulrajaramrahulrajaram

kokoro-tts

Convert text responses into audible speech using the Kokoro TTS Python library.

Community
Basic
SafeAI-Lab-XSafeAI-Lab-X
1.0k

sherpa-onnx-tts

Synthesize offline speech with sherpa-onnx runtimes and models.

Community
Intermediate