$ ~/registry/skill/openai-curated-speech

SKILL

speech

Name: speech
Author: OpenAI

Convert text into voiceovers, accessibility reads, and batch audio prompts.

Stars

★ 23,132

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 22.0k

Summary

This skill is not prompt-only in practice: the documentation explicitly instructs using a local CLI with the OpenAI Audio API and an OPENAI_API_KEY, sending text to OpenAI for speech generation. Because the source is auditable, open-source on GitHub, and widely adopted by the community, the overall rating is better classified as caution rather than risk.

CredentialsCaution

The material explicitly requires an OPENAI_API_KEY for live API calls, which is a sensitive credential. The README also advises users not to paste the full key into chat, which reduces obvious misuse risk, but the credential could still be abused for billed API usage if mishandled or exposed.

Network egressCaution

The skill states that it uses the OpenAI Audio API for speech generation, meaning user-provided text is sent to OpenAI. No other third-party or unrelated endpoints are identified in the material, and the network egress is consistent with the declared functionality.

Code executionCaution

The README instructs running a local script (`scripts/text_to_speech.py`) and installing dependencies via `uv pip install openai` or `python3 -m pip install openai` if missing. This is standard local script execution and dependency installation, with no specific red flags showing requests for unusual system privileges.

Data accessCaution

The material indicates it writes temporary JSONL files under `tmp/speech/`, saves outputs under `output/speech/`, and processes user-provided text. The apparent access scope is mainly intermediate and output files within the working directory; it does not request broad system data access, but it does involve local file writes and content retention.

Supply chainLow risk

The source is an open-source GitHub repository (`openai/skills`) with high community adoption (about 22k stars), making the code auditable and materially lowering risk. Although the license and maintenance status are not clearly stated and it depends on the `openai` Python package, the available material shows no high-risk red flags such as closed-source distribution, obvious abandonment, or suspicious delivery channels.

Recommendations

Set OPENAI_API_KEY locally only when needed, with minimal scope, and avoid exposing it in chat, CLI arguments, or commits.
Before processing sensitive text, confirm that it will be sent to OpenAI and review your organization’s data compliance requirements.
Review `scripts/text_to_speech.py` and dependency versions before use; prefer pinned versions and install in an isolated environment.
Regularly clean `tmp/speech/` and `output/speech/` to avoid long-term retention of batch input text and generated audio.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "speech" skill from askskill:
1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/speech/SKILL.md
2. Save it as ~/.claude/skills/speech/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

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 (scripts/text_to_speech.py) with sensible defaults (see 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.

If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.

Defaults & rules

Use gpt-4o-mini-tts-2025-12-15 unless the user requests another model.
Default voice: cedar. If the user wants a brighter tone, prefer marin.
Built-in voices only. Custom voices are out of scope for this skill.
instructions are supported for GPT-4o mini TTS models, but not for tts-1 or tts-1-hd.
Input length must be <= 4096 characters per request. Split longer text into chunks.
Enforce 50 requests/minute. The CLI caps --rpm at 50.
Require OPENAI_API_KEY before any live API call.
Provide a clear disclosure to end users that the voice is AI-generated.
Use the OpenAI Python SDK (openai package) for all API calls; do not use raw HTTP.
Prefer the bundled CLI (scripts/text_to_speech.py) over writing new one-off scripts.
Never modify scripts/text_to_speech.py. If something is missing, ask the user before doing anything else.

Instruction augmentation

Reformat user direction into a short, labeled spec. Only make implicit details explicit; do not invent new requirements.

Quick clarification (augmentation vs invention):

If the user says "narration for a demo", you may add implied delivery constraints (clear, steady pacing, friendly tone).
Do not introduce a new persona, accent, or emotional style the user did not request.

Template (include only relevant lines):

Voice Affect: <overall character and texture of the voice>
Tone: <attitude, formality, warmth>
Pacing: <slow, steady, brisk>
Emotion: <key emotions to convey>
Pronunciation: <words to enunciate or emphasize>
Pauses: <where to add intentional pauses>
Emphasis: <key words or phrases to stress>

…

View full docs ↗

OpenAIGet→

// similar tools

MCP

text-to-speech

Convert text into multilingual speech and save it as MP3 audio.