skills.rest
bl1nk-bot
bl1nk-botOFFICIAL
Explore all skills by this author →
GitHub

speech

Generate spoken audio from text using the OpenAI Audio API.

3|Updated Feb 13, 2026
Search Tags:#cli#audio#openai#batch#tts#narration#speech
One-click install
npx skills add https://github.com/bl1nk-bot/skills-cli --skill speech-bl1nk-bot
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/bl1nk-bot/skills-cli/tree/main/skills/speech
Command: npx skills add https://github.com/bl1nk-bot/skills-cli --skill speech-bl1nk-bot

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill lets you convert written text into natural-sounding speech using built-in voices and the OpenAI Audio API, enabling narrated content, accessibility reads, and batch generation without leaving your repo.

Core Features & Use Cases

  • Single and batch generation: produce one clip or many outputs for narration, product demos, IVR prompts, and accessibility needs.
  • Bundled CLI: use the included CLI at scripts/text_to_speech.py to drive deterministic runs with sensible defaults and safe fallback handling.
  • Environment & security: requires OPENAI_API_KEY for live calls and supports dry-run mode for local testing.

Quick Start

Run the bundled CLI to synthesize speech from text: use scripts/text_to_speech.py speak --input "Hello" --voice cedar to generate a clip with 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 OpenAI built-in voices?▼

You can generate spoken audio from text by running the bundled CLI script at scripts/text_to_speech.py with your input text and chosen built-in voice. It uses the OpenAI Audio API to synthesize speech with sensible defaults for model and output formats.

Can I do batch text to speech generation for narration and IVR prompts?▼

Yes, batch voice generation is supported for producing multiple audio outputs. You can generate clips in bulk for narration, product demos, IVR prompts, and accessibility reads without leaving your repository environment.

Do I need an OpenAI API key to generate audio from text?▼

Yes, an OPENAI_API_KEY environment variable is required for live audio generation calls. The Skill also supports a dry-run mode for local testing and safe fallback handling without making live API requests.

What are the limitations of using the OpenAI Audio API for text to speech?▼

The Skill enforces input length validation and rate limits to manage OpenAI Audio API constraints. It applies safe fallback handling and sensible defaults, but live synthesis requires a valid API key and network access.

What is the best way to automate text to speech generation in a CLI workflow?▼

The best way to automate speech generation is using the bundled CLI at scripts/text_to_speech.py. It provides deterministic runs with sensible defaults, supporting single prompts or batch generation directly from your command line.

Related Skills

Explore More Content & Communication Skills→
storyclaw-officialstoryclaw-official

speech

Generate speech audio from text using the OpenAI Audio API.

Official
Intermediate
chenluhanchenluhan

speech

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

Community
Intermediate
clsandovalclsandoval

add-voice-transcription

Transcribe WhatsApp voice notes to text using OpenAI Whisper.

Community
Advanced
avivsinaiavivsinai
6

text-to-speech

Convert text to speech audio using the OpenAI TTS API.

Community
Advanced