A workflow for creating spoken audio from written text using OpenAI’s Audio API. Text-to-speech means converting written words into computer-generated speech.

It is for producing single or batch audio clips with built-in voices, delivery instructions, and checks for clarity, pacing, pronunciation, and format.

It removes the need to record every narration, voiceover, accessibility reading, or phone prompt manually.

speech — Skill for Claude Code and Codex by tercumantanumut

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add tercumantanumut/selene --skill speech

Clone the repo

git clone --depth 1 https://github.com/tercumantanumut/selene

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tercumantanumut/selene/speech/github.svg)](https://agentmods.dev/skills/tercumantanumut/selene/speech)

Your own site

<a href="https://agentmods.dev/skills/tercumantanumut/selene/speech"><img src="https://agentmods.dev/badge/skills/tercumantanumut/selene/speech/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tercumantanumut/selene/speech"><img src="https://agentmods.dev/badge/skills/tercumantanumut/selene/speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,867 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 53
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.01867
Opus 5	$0.00039	$0.00933
Sonnet 5	$0.00015	$0.00373
Haiku 4.5	$0.00008	$0.00187

Measured 10d ago against content hash d60904c84bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

speech scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/text_to_speech.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

lib/skills/catalog/bundled/speech/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speech Generation Skill

Generate spoken audio for the current project (narration, product demo voiceover, IVR prompts, accessibility reads). Defaults to gpt-4o-mini-tts-2025-12-15 and built-in voices, and prefers the bundled CLI for deterministic, reproducible runs.

When to use

Generate a single spoken clip from text
Generate a batch of prompts (many lines, many files)

Decision tree (single vs batch)

If the user provides multiple lines/prompts or wants many outputs -> batch
Else -> single

Workflow

Decide intent: single vs batch (see decision tree above).
Collect inputs up front: exact text (verbatim), desired voice, delivery style, format, and any constraints.
If batch: write a temporary JSONL under tmp/ (one job per line), run once, then delete the JSONL.
Augment instructions into a short labeled spec without rewriting the input text.
Run the bundled CLI (${SELENE_SKILL_ROOT}/scripts/text_to_speech.py) with sensible defaults (see ${SELENE_SKILL_ROOT}/references/cli.md).
For important clips, validate: intelligibility, pacing, pronunciation, and adherence to constraints.
Iterate with a single targeted change (voice, speed, or instructions), then re-check.
Save/return final outputs and note the final text + instructions + flags used.

Temp and output conventions

Use tmp/speech/ for intermediate files (for example JSONL batches); delete when done.
Write final artifacts under output/speech/ when working in this repo.
Use --out or --out-dir to control output paths; keep filenames stable and descriptive.

Dependencies (install if missing)

Prefer uv for dependency management.

Python packages:

uv pip install openai

If uv is unavailable:

python3 -m pip install openai

Environment

OPENAI_API_KEY must be set for live API calls.

If the key is missing, give the user these steps:

Create an API key in the OpenAI platform UI: https://platform.openai.com/api-keys
Set OPENAI_API_KEY as an environment variable in their system.
Offer to guide them through setting the environment variable for their OS/shell if needed.

Never ask the user to paste the full key in chat. Ask them to set it locally and confirm when ready.

Read the full file on GitHub · 145 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 145 lines · 77 tokens per session scan A d60904c84bcc

Subscribe to this mod's changes

speech is a skill published in the GitHub repository tercumantanumut/selene (169 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,867 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media agent antigravity codebase-indexing codex deferred-loading diffusion-models

ai-ugc-ads

When the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions 'UGC,' 'user-generated content,' 'creator ads,' 'Spark Ads,' 'whitelisting,' 'AI UGC,' 'Arcads,' 'Creatify,' 'creator brief,' or 'UGC testing.' This skill…

tech-leads-club/agent-skills · 116 tokens

paid-creative-ai

When the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid media with AI tools. Also use when the user mentions 'ad creative,' 'performance creative,' 'creative testing,' 'creative fatigue,' 'Meta ads,' 'Google ads,' 'TikTok ads,' 'AI ads,' 'ad budget,'…