skills.rest
Probably-Group
Probably-GroupOFFICIAL
Explore all skills by this author →
Website𝕏@problynotingGitHub

text-to-speech

Generate local text-to-speech audio from sanitized text using Kokoro TTS.

3|1|Updated Dec 3, 2025
Search Tags:#text-to-speech#speech synthesis#kokoro#streaming playback#audio validation#ssml injection#local llm tools
One-click install
npx skills add https://github.com/Probably-Group/Dev-AID --skill text-to-speech-probably-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/Probably-Group/Dev-AID/tree/main/.dev-aid/skills/expert/text-to-speech
Command: npx skills add https://github.com/Probably-Group/Dev-AID --skill text-to-speech-probably-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you turn text into local audio speech reliably and safely, avoiding common failures like SSML injection, resource exhaustion, and broken audio outputs.

Core Features & Use Cases

  • Secure SSML/Text Handling: Prevents SSML injection and strips/escapes unsafe patterns before synthesis.
  • Resource-Efficient Model Management: Uses a pooled/singleton TTS model with concurrency control to avoid repeated heavyweight loads.
  • Verified Audio Output: Validates generated audio (empty output, NaN/Inf, excessive duration, silence, amplitude issues) before returning results.
  • Production-Oriented TTS Pipelines: Supports voice selection, sentence-based chunking for long text, optional streaming playback patterns, and writing synthesized audio to disk.
  • Recommended Scope: Use for local voice synthesis with Kokoro TTS and SSML-like processing; do not use for cloud TTS APIs.

Quick Start

Use the text-to-speech skill when you need to synthesize spoken audio from user-provided text on your machine using Kokoro TTS, ensuring the text is sanitized and the produced audio is validated before playback or saving.

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 local speech from text safely?▼

Local speech synthesis converts input text to audio using Kokoro TTS, applying input sanitization to mitigate SSML injection and validating audio for NaN, silence, and normalization before returning results.

How does long-text chunking work for streaming playback?▼

Sentence-based long-text chunking splits input text into segments for speech synthesis, enabling optional streaming playback patterns and writing synthesized audio files to disk sequentially.

How do I prevent SSML injection in text-to-speech pipelines?▼

Preventing SSML injection in text-to-speech pipelines requires input sanitization that strips and escapes unsafe patterns before synthesizing text into audio.

Can I use Kokoro TTS for cloud-based speech synthesis?▼

Kokoro TTS is scoped for local voice synthesis and SSML-like processing; you should not use this approach for cloud TTS APIs.

How do I avoid resource exhaustion when loading TTS models?▼

Avoiding resource exhaustion when loading TTS models requires resource-efficient model management, using a pooled or singleton TTS model with concurrency limits to prevent repeated heavyweight loads.

Why does my generated speech audio output fail validation?▼

Speech audio output fails validation when generated files contain empty output, NaN or Inf values, excessive duration, silence, or amplitude normalization issues detected before returning results.

Related Skills

Explore More Software Engineering Skills→
servitolaservitola
12

tts

Synthesize local text-to-speech via configurable multi-backend proxy with fallbacks.

Community
Advanced
ai-shifuai-shifu
309

listen-mode-audio-streaming

Manage real-time streaming audio with buffering and source prioritization.

Official
Advanced
tedtv1007-ctrltedtv1007-ctrl

sag

Synthesize ElevenLabs text-to-speech audio with local playback.

Community
Intermediate
Yogi-076Yogi-076

sherpa-onnx-tts

Synthesize WAV audio from plain text using sherpa-onnx runtime.

Community
Intermediate