speech

Name: speech
Availability: InStock
Author: chenluhan

Generate spoken audio from text using built-in voices and the bundled CLI.

Updated Apr 15, 2026

Search Tags:#cli #audio #openai #batch #tts #narration #speech

Ready to run

npx skills add https://github.com/chenluhan/skill --skill speech-chenluhan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/chenluhan/skill/tree/main/.agents/skills/speech
Command: npx skills add https://github.com/chenluhan/skill --skill speech-chenluhan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

The Speech Generation Skill turns text into spoken audio for narration, accessibility reads, IVR prompts, and product demos, using built-in voices and a bundled CLI, with live calls requiring OPENAI_API_KEY.

Core Features & Use Cases

Built-in voices (e.g., cedar, marin) for deterministic speech output
Single and batch generation via the bundled CLI
Output to common formats (mp3, wav, etc.) with deterministic output paths
Clear guidance on environment setup and safety disclosures

Quick Start

Run the bundled CLI to generate speech from text using the default voice and format.

Frequently Asked Questions about speech

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

FAQPage Schema

How do I generate spoken audio from text for narration and IVR prompts?▼

To generate spoken audio from text, this skill uses a bundled CLI to process single or batch text inputs into natural speech using built-in voices like cedar and marin. It outputs common formats such as mp3 and wav for narration, accessibility reads, IVR prompts, and product demos.

Do I need an OpenAI API key to generate speech with the CLI?▼

Yes, you need an OpenAI API key to generate speech with the CLI. Live API calls require the OPENAI_API_KEY environment variable to be set. The skill also performs input validation on length, voice, and format parameters before sending requests.

Can I process multiple text files for batch text to speech generation?▼

Yes, you can process multiple text files for batch text to speech generation. The bundled CLI supports both single and batch speech generation, allowing you to produce multiple audio files with deterministic output paths in formats like mp3 and wav.

What audio formats are supported when converting text to speech?▼

When converting text to speech, supported audio formats include common types like mp3 and wav. The skill validates format parameters during input and generates audio files with deterministic output paths to ensure consistent batch processing results.

What are the limitations of using built-in voices for text to speech generation?▼

The limitation of using built-in voices for text to speech generation is that voice selection is restricted to predefined options like cedar and marin for deterministic output. Additionally, all live synthesis requires a valid OPENAI_API_KEY and strict input validation on length, voice, and format parameters.