text-to-speech

Convert text to speech using multiple TTS providers.

3|2|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/ryan-mt/claude-backup --skill text-to-speech-ryan-mt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/ryan-mt/claude-backup/tree/main/config/skills/text-to-speech
Command: npx skills add https://github.com/ryan-mt/claude-backup --skill text-to-speech-ryan-mt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires edge-tts, elevenlabs, openai, google-cloud-texttospeech, falai, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of converting text to speech, providing high-quality audio output from multiple TTS providers.

Core Features & Use Cases

  • Multiple TTS Providers: Supports ElevenLabs, OpenAI, Google Cloud, fal.ai CSM-1B, and edge-tts.
  • Smart Routing: Routes requests based on quality, cost, and latency requirements.
  • Use Cases: Ideal for voiceovers, narrations, batch document conversion, and multilingual speech synthesis.

Quick Start

Generate a speech audio file from text using the text-to-speech skill.

Frequently Asked Questions about text-to-speech

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

FAQPage Schema
How do I convert text to speech using multiple providers?

You can convert text to speech by routing requests through supported providers like ElevenLabs, OpenAI, Google Cloud, and edge-tts. The skill automatically manages the audio synthesis process based on your quality, cost, and latency requirements.

What is the best way to generate voiceovers for batch document conversion?

The best way to generate voiceovers for batch documents is using the skill's smart routing feature. It processes large volumes of text into high-quality audio by selecting the optimal text-to-speech provider for your specific narration needs.

Does this text-to-speech skill support multilingual speech synthesis?

Yes, the text-to-speech skill supports multilingual speech synthesis. By leveraging multiple providers like Google Cloud and OpenAI, it can generate narrations and voiceovers across various languages suitable for diverse content.

Can I use edge-tts for audio conversion without high API costs?

Yes, you can use edge-tts for audio conversion to minimize costs. The skill includes edge-tts alongside premium options like ElevenLabs, allowing smart routing to balance quality and latency while keeping expenses low.

Do I need Python libraries to run this speech synthesis tool?

Yes, you need Python libraries for TTS and audio processing to run this speech synthesis tool. These dependencies are required to execute the scripts that interface with the supported providers and generate the final audio files.

When should I use ElevenLabs versus fal.ai CSM-1B for narration?

Use ElevenLabs for premium quality voiceovers and fal.ai CSM-1B for specialized speech synthesis. The skill's smart routing evaluates your quality, cost, and latency constraints to automatically select the most appropriate provider for your narration.