speech — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited speech (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
scripts/text_to_speech.py) with sensible defaults (see references/cli.md).tmp/speech/ for intermediate files (for example JSONL batches); delete when done.output/speech/ when working in this repo.--out or --out-dir to control output paths; keep filenames stable and descriptive.Prefer uv for dependency management.
Python packages:
uv pip install openaiIf uv is unavailable:
python3 -m pip install openaiOPENAI_API_KEY must be set for live API calls.If the key is missing, give the user these steps:
OPENAI_API_KEY as an environment variable in their system.If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.
gpt-4o-mini-tts-2025-12-15 unless the user requests another model.cedar. If the user wants a brighter tone, prefer marin.instructions are supported for GPT-4o mini TTS models, but not for tts-1 or tts-1-hd.--rpm at 50.OPENAI_API_KEY before any live API call.openai package) for all API calls; do not use raw HTTP.scripts/text_to_speech.py) over writing new one-off scripts.scripts/text_to_speech.py. If something is missing, ask the user before doing anything else.Reformat user direction into a short, labeled spec. Only make implicit details explicit; do not invent new requirements.
Quick clarification (augmentation vs invention):
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>
Delivery: <cadence or rhythm notes>Augmentation rules:
Input text: "Welcome to the demo. Today we'll show how it works."
Instructions:
Voice Affect: Warm and composed.
Tone: Friendly and confident.
Pacing: Steady and moderate.
Emphasis: Stress "demo" and "show".{"input":"Thank you for calling. Please hold.","voice":"cedar","response_format":"mp3","out":"hold.mp3"}
{"input":"For sales, press 1. For support, press 2.","voice":"marin","instructions":"Tone: Clear and neutral. Pacing: Slow.","response_format":"wav"}More principles: references/prompting.md. Copy/paste specs: references/sample-prompts.md.
Use these modules when the request is for a specific delivery style. They provide targeted defaults and templates.
references/narration.mdreferences/voiceover.mdreferences/ivr.mdreferences/accessibility.mdreferences/cli.mdreferences/audio-api.mdreferences/voice-directions.mdreferences/codex-network.mdscripts/text_to_speech.py (commands, flags, recipes).~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.