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 yangkun19921001/PP-Claw --skill edge-ttsgit clone --depth 1 https://github.com/yangkun19921001/PP-ClawWrote 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/yangkun19921001/pp-claw/edge-tts)<a href="https://agentmods.dev/skills/yangkun19921001/pp-claw/edge-tts"><img src="https://agentmods.dev/badge/skills/yangkun19921001/pp-claw/edge-tts/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/yangkun19921001/pp-claw/edge-tts"><img src="https://agentmods.dev/badge/skills/yangkun19921001/pp-claw/edge-tts.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 | $0.00056 | $0.01267 |
| Opus 5 | $0.00028 | $0.00633 |
| Sonnet 5 | $0.00011 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
edge-tts 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 11d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge-TTS Skill
Generate high-quality text-to-speech audio using Microsoft Edge's neural TTS service via node-edge-tts. Free, no API key required.
Quick Start
When user requests TTS conversion, use shell_exec to run the converter script:
# First time: install dependencies
cd <SKILL_DIR>/scripts && npm install --production
# Convert text to speech
node <SKILL_DIR>/scripts/tts-converter.js "Your text here" --voice zh-CN-XiaoxiaoNeural --output /tmp/output.mp3
Replace <SKILL_DIR> with the actual skill directory path (use pwd or the skill's location).
Trigger Detection
Recognize these as TTS requests:
- "tts", "text to speech", "text-to-speech"
- User explicitly asks to convert text to audio/voice/speech
- User wants content read aloud
Usage
Basic Conversion
node scripts/tts-converter.js "Hello world" --output hello.mp3
With Voice and Rate
node scripts/tts-converter.js "Hello world" \
--voice en-US-AriaNeural \
--rate +10% \
--output hello.mp3
List Available Voices
node scripts/tts-converter.js --list-voices
Configuration Manager
# Set default voice
node scripts/config-manager.js --set-voice zh-CN-XiaoxiaoNeural
# Set default rate
node scripts/config-manager.js --set-rate +10%
# View current settings
node scripts/config-manager.js --get
# Reset to defaults
node scripts/config-manager.js --reset
CLI Options
| Option | Short | Description | Default |
|---|---|---|---|
--voice |
-v |
Voice name | en-US-MichelleNeural |
--lang |
-l |
Language code | en-US |
--format |
-o |
Audio format | audio-24khz-48kbitrate-mono-mp3 |
--pitch |
Pitch adjustment | default |
|
--rate |
-r |
Speed adjustment | default |
--volume |
Volume adjustment | default |
|
--save-subtitles |
-s |
Save subtitles JSON | false |
--output |
-f |
Output file path | temp file |
--proxy |
-p |
Proxy URL | - |
--timeout |
Timeout in ms | 10000 |
|
--list-voices |
-L |
List voices | - |
What ships with it
4 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.
- 11d ago First seen · 150 lines · 56 tokens per session scan A 36f530189fd2
edge-tts is a skill published in the GitHub repository yangkun19921001/PP-Claw (37 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 1,267 once invoked, about $0.0003 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.
Other skills, from other repositories
pn-tts
Text-to-speech for video and audio production. Covers tool selection (ElevenLabs, OpenAI, Kokoro/local), voice and model choice, SSML expressivity, caption-track alignment (SRT/VTT), loudness normalization, retry strategy, and accessibility requirements. Use when a composition or generative video needs narration audio…
multilingual-campaign
Turn one Canvora generation into a native multilingual campaign — generate once, convert per language with layout-preserving localization. 150+ languages including RTL (Arabic, Hebrew, Urdu) and CJK. Use when the user wants social visuals in multiple languages, localized campaigns, translated posts, or content for…
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
gpt-image-2-style-library
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…