speech
nexu-io/open-design
Generate spoken audio from text using OpenAI's text-to-speech API with multiple voices.
What is speech?
This skill converts text into natural-sounding spoken audio using OpenAI's TTS engine. Use it to create narrated explainers, lecture audio, voiceover tracks, or any audio content from written text.
- Generate spoken audio from text using OpenAI's API
- Access multiple built-in voices for different narration styles
- Create narrated explainers and educational content
- Produce voiceover tracks for videos or presentations
- Generate lecture audio from written content
How to install speech
npx skills add https://github.com/nexu-io/open-design --skill speech- OpenAI API key with access to the text-to-speech API
- Active agent with skills directory support
How to use speech
- 1.Install the upstream bundle from https://github.com/openai/skills into your agent's skills directory
- 2.Ask the agent to invoke the skill by name (speech) or use trigger phrases like 'openai speech', 'tts openai', 'narrated audio', or 'voice over'
- 3.Provide the text you want converted to speech
- 4.Specify voice preference if needed (from available OpenAI voices)
- 5.The skill will generate and return the audio file
Use cases
- Creating narrated video explainers or tutorials
- Generating audio versions of blog posts or articles
- Producing voiceover tracks for presentations
- Creating accessible audio content from text documents
- Building narrated educational or training materials
- Content creators and educators
- Video producers and filmmakers
- Accessibility specialists
- Technical writers
- Marketing and communications teams
speech FAQ
The skill uses OpenAI's built-in voices. Refer to the upstream repository at https://github.com/openai/skills for the complete list of available voice options.
Refer to the OpenAI TTS API documentation in the upstream repository for supported output formats and quality settings.
Yes, you need an active OpenAI API key with access to the text-to-speech API to use this skill.
Usage rights depend on your OpenAI API agreement. Check OpenAI's terms of service for commercial use policies.
Full instructions (SKILL.md)
Source of truth, from nexu-io/open-design.
name: speech description: | Generate spoken audio from text using OpenAI's API with built-in voices. Useful for narrated explainers, lecture audio, and quick voiceover tracks. triggers:
- "openai speech"
- "tts openai"
- "narrated audio"
- "voice over" od: mode: audio category: audio-music upstream: "https://github.com/openai/skills"
speech
Curated from OpenAI's skills repository.
What it does
Generate spoken audio from text using OpenAI's API with built-in voices. Useful for narrated explainers, lecture audio, and quick voiceover tracks.
Source
- Upstream: https://github.com/openai/skills
- Category:
audio-music
How to use
This catalogue entry advertises the skill in OpenDesign so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory:
# Inspect the upstream README for exact paths
open https://github.com/openai/skills
Then ask the agent to invoke this skill by name (speech) or with
one of the trigger phrases listed in this skill's frontmatter.
Related skills
More from nexu-io/open-design and the wider catalog.
stitch-design-taste
Generate premium, anti-generic DESIGN.md files for Google Stitch with strict typography, color calibration, and semantic design rules.
stitch-loop
Iterative design-to-code feedback loop for tightening visual fidelity between brief and built UI.
swiftui-design
SwiftUI design system with anti-slop rules, brand protocols, and multi-dimensional review for iOS frontends.
swiss-creative-mode-template
Premium Swiss/editorial HTML template with bold typography, interactive navigation, and theme switching.
swiss-user-research-video-template
Premium Swiss-editorial user research template with warm paper aesthetics and keyboard-navigable slides.
taste-skill
|