技能详情（站内镜像，无评论）
作者：Danny Shmueli @dannyshmueli
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.1
统计：⭐ 0 · 154 · 1 current installs · 1 all-time installs
⭐ 0
安装量（当前） 1
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：dannyshmueli/edge-tts-unlimited
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill does what it claims (wraps the Python edge-tts package via a small shell script) and does not request unrelated credentials or perform obvious exfiltration, but it auto-installs Python packages globally and makes platform-specific path assumptions that you should review before use.
目的
Name/description (unlimited Edge TTS via edge-tts) match the included script and instructions. The script invokes edge-tts with expected options (voice, rate, file/text, list voices). No unrelated services, credentials, or binaries are required.
说明范围
SKILL.md simply instructs running scripts/speak.sh with text or file. The script only reads an optional input file you provide, writes output to a specified path (default /tmp), lists voices, and invokes edge-tts. It does not attempt to read unrelated system files or environment variables.
安装机制
There is no formal install spec, but the script will auto-install the PyPI package edge-tts by running 'pip3 install -q edge-tts' when edge-tts is not available. This is a dynamic, on-demand install from PyPI (not a vetted release host) and does not create or use a virtual environment; it may install packages into the global environment. The script also prefers a 'uv' runner if present, checking hard-coded paths (/data/clawd/.local/bin/uv, /ho…
证书
The skill declares no required env vars or credentials and the script does not read credentials. It only references optional input files you pass and writes outputs to an output path. The lack of credential requests is proportionate to the TTS purpose.
持久
always is false and the skill does not request persistent agent-level privileges. It does not modify other skills or global agent configuration. The main privilege is that it can install a Python package on first run (see install_mechanism note).
综合结论
This skill is internally consistent for its stated TTS purpose, but review these points before installing or running it in a shared environment: - It may run 'pip3 install -q edge-tts' automatically and without a virtual environment, which can modify the host Python environment. Prefer running it inside a container, dedicated VM, or create a Python virtualenv before running. - The script suppresses installer output and errors (redirects to /de…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Edge Tts Unlimited」。简介：Free, unlimited text-to-speech using Microsoft Edge neural voices via Python ed…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/dannyshmueli/edge-tts-unlimited/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: edge-tts-unlimited
description: Free, unlimited text-to-speech using Microsoft Edge neural voices via Python edge-tts. Use when generating long-form audio, podcasts, voice notes, spoken briefs, or headless/server-side TTS without API keys, credits, or character limits.
---
# Edge TTS Unlimited
Free, unlimited neural TTS. No API key. No credits. No character limits.
## Use this skill for
- long-form audio generation
- spoken briefs and voice notes
- server-side or headless TTS on Fly.io, VPS, or Docker
- cases where paid TTS quotas are unnecessary
Prefer this skill over premium TTS when cost and length matter more than voice cloning or premium voice acting.
## Quick start
Generate from text:
```bash
scripts/speak.sh "Hello world" -o output.mp3
```
Generate from file:
```bash
scripts/speak.sh --file /tmp/my-script.txt -o output.mp3
```
With voice and speed:
```bash
scripts/speak.sh --file script.txt -v en-US-GuyNeural -r "+5%" -o brief.mp3
```
## Requirements
- Python 3.8+
- `uv` preferred, or `pip`
The script auto-detects `uv`, falls back to `pip`, and runs `edge-tts` without requiring a dedicated venv.
## Voice presets
- `news-us` → `en-US-GuyNeural` +5%
- `news-bbc` → `en-GB-RyanNeural`
- `calm` → `en-US-AndrewNeural` -10%
- `fast` → `en-US-ChristopherNeural` +20%
Example:
```bash
scripts/speak.sh --file brief.txt --preset news-us -o brief.mp3
```
## Options
```bash
scripts/speak.sh [TEXT] [OPTIONS]
TEXT Text to speak (or use --file)
--file, -f FILE Read text from file
--voice, -v NAME Voice name (default: en-US-GuyNeural)
--rate, -r RATE Speed adjustment like "+5%" or "-10%"
--preset, -p NAME Use a preset voice profile
--output, -o FILE Output path (default: /tmp/tts-{timestamp}.mp3)
--list List available voices
--list-filter STR Filter voice list
```
## Useful voices
- `en-US-GuyNeural` — strong default for briefs
- `en-US-ChristopherNeural` — authoritative US male
- `en-US-AriaNeural` — confident US female
- `en-GB-RyanNeural` — steady British male
- `en-GB-SoniaNeural` — British female
List voices:
```bash
scripts/speak.sh --list
scripts/speak.sh --list-filter british
scripts/speak.sh --list-filter female
```
## Notes
- Use `--file` for anything longer than a short sentence.
- `+5%` sounds natural for news and summaries.
- Output is compact MP3 suitable for voice content.
- This is not for real-time streaming, voice cloning, or premium character acting.