speech

Name: speech
Availability: InStock
Author: JetBrains

Convert input text into mp3 or wav speech audio via a bundled CLI.

302|22|Updated Feb 12, 2026

Search Tags:#cli #text-to-speech #openai #tts #batch-processing #audio-generation #voices

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Convert input text into natural-sounding speech audio to support narration, accessibility reads, voice prompts, and product demos without recording.

Core Features & Use Cases

Bundled CLI-based TTS with built-in voices for deterministic runs
Single and batch generation (speak and speak-batch) to handle one-off and multi-line inputs
Output formats and config: supports mp3, wav, and other formats; configurable speed and optional instructions
Requiring OPENAI_API_KEY for live calls; runs locally in your environment

Quick Start

Set OPENAI_API_KEY and run the bundled CLI with your input text to generate speech using the built-in voices.

Frequently Asked Questions about speech

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

FAQPage Schema

How do I convert text to speech using a CLI with OpenAI?▼

You can convert text to speech by running the bundled CLI with your input text after setting the OPENAI_API_KEY environment variable, which generates natural-sounding speech using built-in voices.

Can I generate speech audio in mp3 and wav formats?▼

Yes, the text-to-speech CLI supports output formats including mp3 and wav, allowing you to generate natural speech audio files for narration, accessibility, and product demos.

What is the best way to batch process text-to-speech generation?▼

The best way to batch process text-to-speech generation is using the bundled speak-batch CLI command, which handles multi-line inputs to create multiple natural speech audio files efficiently.

Do I need an OpenAI API key to run text-to-speech locally?▼

Yes, you need an OPENAI_API_KEY to run the text-to-speech CLI locally for live calls, as the bundled tool requires it to generate natural-sounding speech audio from input text.

Can I configure speed and instructions for AI voice generation?▼

Yes, the AI voice generation CLI supports configurable speed and optional instructions, allowing you to customize the natural-sounding speech output alongside selecting from built-in voices.