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.
npx skills add thewolffish/wolffish-app --skill text-to-speechgit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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.
[](https://agentmods.dev/skills/thewolffish/wolffish-app/text-to-speech)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/text-to-speech"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/text-to-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.
<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/text-to-speech"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/text-to-speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00049 | $0.02685 |
| Opus 5 | $0.00024 | $0.01342 |
| Sonnet 5 | $0.00010 | $0.00537 |
| Haiku 4.5 | $0.00005 | $0.00268 |
Grade A, and why
text-to-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 5d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice
Interface
- Tools:
voice_generate,voice_respond,voice_list - Engine: Kokoro — a local 82M-parameter neural TTS model. Runs entirely on-device (CPU) via a managed Python runtime; no cloud, no API key, no account.
- Output: MP3 files stored in the workspace voice directory.
The first voice memo provisions the engine (a hermetic Python runtime, the kokoro-onnx package, and the ~310 MB model) — this is a one-time download. Every voice memo after that is fully offline.
You can also provision it up front with voice_engine_install — worth doing
when the user asks to set voice up, or when a first memo would otherwise stall
on a several-minute download with no explanation. voice_settings_get reports
whether it is already installed.
When to use each tool
- The user's message is tagged
<voice_note>(they spoke instead of typing) → follow the<voice_prompts>block when your prompt carries one — it is present exactly when the Voice replies switch (Preferences page, default ON) is on, and it makes the rule explicit: the turn MUST end with exactly onevoice_respondspeaking the answer — a conversational answer is the memo and nothing else; a working turn delivers files/tables/code exactly as a typed turn would, then closes with the memo. Only an explicit ask in the user's own message ("reply in text") overrides it. No<voice_prompts>block in your prompt means the switch is off — reply as normal text. - "convert this to a voice memo", "read this aloud", "say this" →
voice_generatewith the specified text. The voice memo attaches below your text response. - "respond in voice", "reply with audio", "voice memo only" →
voice_respondwith your full response. Do NOT also send the text as a regular message — the voice IS the response. Write only a brief label like "Voice memo" as your text output. - "summarize the last response as a voice memo" → Condense your most recent response into spoken form and use
voice_respond. - "from now on reply with voice memos" → Use
voice_respondfor all subsequent responses until told otherwise. - "list my voice memos" →
voice_list. - "use a British voice from now on", "talk slower", "what voice are you using?" → the settings tools below. Changing a default is something you do, not something you send the user to Settings for.
What ships with it
2 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.
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.
- 5d ago Changed · +75 lines bf6460248900
- 10d ago First seen · 159 lines · 49 tokens per session scan A 97d30f78ff3f
text-to-speech is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 2,685 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
make-viral-video
Build a short news-explainer video tuned for shareability. One striking moment per video; real fetched assets; self-heal validation; pluggable TTS (Gemini-free default, OpenAI fallback).
gemini-tts
Render text to mp3 via Google Gemini Flash TTS. Free-tier eligible (1500 req/day). Use for video narration, demo voiceovers, audio notes. Parallels openai-tts; default for make-viral-video.
image-generation
Generate and edit images using Gemini Flash Image, and generate videos using Veo. Supports text-to-image, image editing, text-to-video, and image-to-video.
audio-transcribe
Transcribes audio files and voice notes to text via Gemini 2.5-flash. Integrates with Slack, Discord, and Telegram bridges so voice clips surface as readable text in tasks.
screen-record
Start or stop a screen recording of the Mac via ffmpeg. Use when the user asks to record/capture their screen to a video file (a demo, a repro, a walkthrough) — not for a single still screenshot (use macos-tools screen capture for that).
openai-tts
Render text to mp3 via OpenAI's tts-1-hd. Use for video narration, demo voiceovers, audio notes.