skills.rest
valtterimelkko
valtterimelkkoCOMMUNITY
Explore all skills by this author →
GitHub

text-to-speech

Convert text input into WAV audio files using a local ONNX runtime.

1|1|Updated Jun 11, 2026
Search Tags:#synthesis#audio#local#tts#onnx#speech
One-click install
npx skills add https://github.com/valtterimelkko/agent-workflow-skills --skill text-to-speech-valtterimelkko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/valtterimelkko/agent-workflow-skills/tree/main/skills/text-to-speech
Command: npx skills add https://github.com/valtterimelkko/agent-workflow-skills --skill text-to-speech-valtterimelkko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires supertonic, soundfile, and includes scripts (resource) components.

What problem does it solve?

This skill solves the need for high-quality, private, and offline speech synthesis, removing reliance on expensive cloud APIs or GPU-heavy infrastructure.

Core Features & Use Cases

  • Local Synthesis: Converts text to 44.1kHz WAV audio entirely on your CPU using the Supertonic engine.
  • Multilingual Support: Provides native-sounding speech across 31 languages with 10 distinct voice styles.
  • Use Case: Perfect for generating voiceovers for video projects, creating accessible audio versions of documents, or building local-first voice interfaces for applications.

Quick Start

Use the text-to-speech skill to synthesize the provided text into an audio file named output.wav using the M1 voice style.

Frequently Asked Questions about text-to-speech

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

FAQPage Schema
How do I generate audio from text locally without using cloud APIs?▼

You can perform local text-to-speech synthesis by running an ONNX runtime engine on your CPU, converting text input directly into 44.1kHz WAV audio files without relying on cloud APIs or GPU infrastructure.

Does local text-to-speech synthesis support multiple languages and voice styles?▼

Local text-to-speech synthesis supports native-sounding speech across 31 languages and provides 10 distinct voice styles, allowing you to select specific outputs for media production and accessibility tools.

Do I need a GPU to convert text to speech files offline?▼

You do not need a GPU to convert text to speech files offline. The synthesis runs entirely on your CPU using a local ONNX runtime engine, producing 44.1kHz WAV audio files without requiring GPU-heavy infrastructure.

What Python packages are required for offline speech synthesis?▼

Offline speech synthesis requires the supertonic Python package alongside the soundfile dependency and standard system audio libraries to successfully generate and save WAV audio files locally.

What are the limitations of CPU-based ONNX speech synthesis?▼

CPU-based ONNX speech synthesis is limited to generating 44.1kHz WAV audio files and requires local execution, making it less suitable for high-throughput real-time streaming applications compared to GPU-accelerated cloud alternatives.

Related Skills

Explore More Content & Communication Skills→
amdamd
154

quark-install

Installs AMD Quark and verifies its Python package environment after PyTorch setup.

Official
Advanced
Clos01Clos01
3

audio-jingle

Generate music, voiceovers, and sound effects as MP3 or WAV files.

Community
Advanced
kcns008kcns008
5

sherpa-onnx-tts

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

Community
Intermediate
zhcndoczhcndoc

sherpa-onnx-tts

Convert text to speech into an audio file using the sherpa-onnx runtime.

Official
Intermediate