VoiceTTS

Convert text to speech via Edge TTS, ElevenLabs, or Google Cloud TTS.

Updated Apr 12, 2026

Search Tags:#accessibility #voice #text-to-speech #tts #edge-tts #audio-output #google-cloud-tts

Ready to run

npx skills add https://github.com/bharthraj1412/myai --skill voicetts

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: VoiceTTS
Source: https://github.com/bharthraj1412/myai/tree/main/skills/VoiceTTS
Command: npx skills add https://github.com/bharthraj1412/myai --skill voicetts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts written text into natural speech for real-time read-aloud, accessibility, and hands-free interactions.

Core Features & Use Cases

Multi-provider support: Edge TTS (free), ElevenLabs (premium), Google Cloud TTS.
Local voice server integration: Streams audio via a local voice server at localhost:8888.
Configurability: Voice identity and provider selection managed through settings.json.

Quick Start

Provide the text to be spoken and VoiceTTS will read it aloud using the configured voice.

Frequently Asked Questions about VoiceTTS

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

FAQPage Schema

How do I convert text to speech using multiple TTS providers?▼

Text-to-speech conversion across multiple providers is handled by streaming audio through a local voice server at localhost:8888, using Edge TTS, ElevenLabs, or Google Cloud TTS configured via settings.json to produce audible output.

What is the best way to add voice output to accessibility features or conversational agents?▼

Adding voice output for accessibility or conversational agents is achieved by routing text through multi-provider text-to-speech conversion, generating natural speech for real-time read-aloud across local apps and browsers.

Do I need a local voice server to use Edge TTS and Google Cloud TTS for audio output?▼

Yes, a local voice server running at localhost:8888 is required to handle audio streaming and manage provider configurations like Edge TTS and Google Cloud TTS for generating audible text-to-speech output.

Can I switch between free and premium text-to-speech voices?▼

Switching between free and premium text-to-speech voices is done by updating the provider selection and voice identity within the settings.json file to use Edge TTS for free access or ElevenLabs for premium output.

Why is my text-to-speech audio not working during local app read-aloud?▼

Text-to-speech audio output fails if the local voice server is not running at localhost:8888, or if required provider configurations for Edge TTS, ElevenLabs, or Google Cloud TTS are missing from settings.json.