skills.rest
Estom
EstomCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

speech

Generate narrated audio from text via the OpenAI Audio API.

Updated Mar 17, 2026
Search Tags:#accessibility#text-to-speech#openai#tts#voiceover#batch-processing#speech-synthesis
One-click install
npx skills add https://github.com/Estom/aiflex --skill speech-estom
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/Estom/aiflex/tree/main/skills-repo/openai-skills/speech
Command: npx skills add https://github.com/Estom/aiflex --skill speech-estom

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Convert plain text into high-quality spoken audio for narration, demos, IVR prompts, accessibility reads, and batch speech generation without crafting custom TTS pipelines.

Core Features & Use Cases

  • CLI-driven single-clip and JSONL batch generation using a bundled Python tool that calls the OpenAI Audio API.
  • Sensible defaults and guardrails: default model and voice, input length checks, rate-limit enforcement, dry-run mode, retries for transient errors, and explicit requirement for OPENAI_API_KEY.
  • Use cases include creating product demo voiceovers, accessibility audio readouts, IVR prompts, and bulk generation of many short prompts for automated workflows.

Quick Start

Generate a single narrated clip from provided text using the bundled CLI and the default cedar voice.

Frequently Asked Questions about speech

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

FAQPage Schema
How do I generate text-to-speech audio for multiple files in batch?▼

Batch speech synthesis is handled by a bundled Python CLI tool that processes JSONL inputs to call the OpenAI Audio API, generating multiple narrated audio clips with enforced rate limits.

Can I use OpenAI TTS to create voiceovers for product demos and IVR prompts?▼

Yes, OpenAI TTS can create voiceovers for product demos and IVR prompts by passing your script text to the bundled CLI, which applies default voices and guardrails for deterministic audio generation.

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

Yes, text-to-speech batch processing explicitly requires an OPENAI_API_KEY environment variable to authenticate requests to the OpenAI Audio API for generating your narrated audio clips.

What are the limitations when using OpenAI audio API for speech synthesis?▼

Limitations of OpenAI speech synthesis include enforced input length checks and rate limits, though the bundled CLI provides dry-run mode and automatic retries for transient API errors to ensure stability.

What's the best way to add accessibility readouts to text content?▼

The best way to add accessibility readouts is converting text into spoken audio using the bundled speech synthesis CLI, which provides sensible defaults and guardrails for high-quality audio generation.

Does the bundled text-to-speech tool support different voice models and formats?▼

Yes, the text-to-speech tool enforces model, voice, and response format configurations, allowing you to specify parameters for the OpenAI Audio API while defaulting to the cedar voice for quick starts.

Related Skills

Explore More Content & Communication Skills→
shirulotshirulot

speech

Generate spoken audio from text using the OpenAI Audio API.

Community
Intermediate
ollieb89ollieb89

speech

Convert text into natural-sounding mp3 speech audio via the bundled CLI.

Community
Intermediate
kcns008kcns008
5

sherpa-onnx-tts

Generates offline text-to-speech audio from plain text using sherpa-onnx runtime and voice models.

Community
Intermediate
openaiopenai
24.7k

speech

Generate spoken audio from text via the OpenAI Audio API.

Official
Intermediate