Skip to content
mcp/skillhub

Agent Skill

Speech skill

speechOpenAI Skillsskills/.curated/speech/SKILL.md

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

28kofficial repo

always on

70 tokname + description

once used

1,628 tokSKILL.md body

bundled files

151 scripts

repo stars

28kGitHub

Install the Speech skill

Skills CLI (Claude Code, Codex, Cursor and others)

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

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/openai/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -R /tmp/skills/skills/.curated/speech ~/.claude/skills/speech

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description70 tok
When the agent uses itThe SKILL.md instructions1,628 tok
Only if opened15 bundled files (41 KB)varies

Until it is used, speech costs about 19× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 44 skills from openai/skills would load 2,975 tokens of descriptions. Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Speech Generation Skill
  • When to use
  • Decision tree (single vs batch)
  • Workflow
  • Temp and output conventions
  • Dependencies (install if missing)
  • Environment
  • Defaults & rules
  • Instruction augmentation
  • Examples
  • Single example (narration)
  • Batch example (IVR prompts)
  • Instructioning best practices (short list)
  • Guidance by use case
  • CLI + environment notes
  • Reference map

More skills from openai/skills

All skills in this repo
  1. aspnet-coreopenai/skills

    Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.

    28k79 tok idle · 1,065 in use
  2. chatgpt-appsopenai/skills

    Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

    28k196 tok idle · 4,080 in use
  3. cli-creatoropenai/skills

    Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

    28k82 tok idle · 2,222 in use
  4. cloudflare-deployopenai/skills

    Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

    28k43 tok idle · 1,747 in use
  5. define-goalopenai/skills

    Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.

    28k76 tok idle · 1,054 in use
  6. figmaopenai/skills

    Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

    28k59 tok idle · 588 in use
  7. figma-code-connect-componentsopenai/skills

    Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.

    28k181 tok idle · 4,044 in use
  8. figma-create-design-system-rulesopenai/skills

    Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.

    28k170 tok idle · 3,888 in use