技能详情（站内镜像，无评论）
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 · 369 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：可疑 · OpenClaw ：可疑
Package：adriano-vr/ressemble
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：可疑
OpenClaw 评估
The skill implements Resemble TTS/STT via shell scripts and an API key (RESEMBLE_API_KEY) which is coherent with its purpose, but metadata inconsistencies about required environment variables and binaries raise concerns and should be fixed before trusting the skill.
目的
The name/description (Resemble TTS & STT) matches the included scripts and docs: both scripts call Resemble API endpoints for transcription and synthesis. Requiring an API key for Resemble is expected. However, the registry metadata lists no required env vars or binaries while the included .md files and scripts require RESEMBLE_API_KEY and binaries (curl, jq, base64). This metadata mismatch is inconsistent.
说明范围
The SKILL.md and the two shell scripts only perform expected actions: upload an audio file for STT, poll for job status, request TTS synth, decode base64 audio to /tmp, and echo outputs. They do not try to read unrelated system files or additional environment variables. They send data to Resemble endpoints and write temporary files under /tmp, which is consistent with the stated purpose.
安装机制
There is no install specification (instruction-only plus included shell scripts). That is low-risk compared with arbitrary downloads. The presence of executable shell scripts means code will run if invoked, but nothing in the repository performs remote code installation.
证书
The scripts and per-command metadata require RESEMBLE_API_KEY and binaries (curl, jq, base64). The registry-level metadata, however, lists no required env vars or binaries. This divergence is concerning because an omitted required credential or binary in registry metadata could cause unexpected runtime prompts or silent failures and hides that the skill needs your API key. RESEMBLE_API_KEY is the only credential the scripts use; otherwise the …
持久
The skill is not always-enabled and does not request special persistence or modify other skills. It only writes temporary output files to /tmp when synthesizing audio, which is reasonable for its function.
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「Ressemble TTS e STT」。简介：Text-to-Speech and Speech-to-Text integration using Resemble AI HTTP API.。
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/adriano-vr/ressemble/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: ressemble
displayName: Ressemble - Adriano
version: 1.0.0
description: Text-to-Speech and Speech-to-Text integration using Resemble AI HTTP API.
author: Adriano Vargas
tags: [tts, stt, audio, ai, voice]
---
# Ressemble – Text & Voice AI Integration
This skill integrates OpenClaw with the Resemble AI HTTP API, enabling:
- 🎙 Speech-to-Text (audio transcription)
- 🔊 Text-to-Speech (voice synthesis)
It uses direct HTTP calls to Resemble's production endpoints and supports asynchronous transcription polling.
---
## Features
### resemble-tts
Generate high-quality speech audio from text input.
Supports:
- Custom `voice_uuid`
- MP3 output format
- Base64 audio return
### resemble-stt
Transcribe audio files to text using Resemble AI.
Supports:
- Multipart audio upload
- Automatic polling until transcription is complete
- Returns clean transcript text
---
## Requirements
You must define the environment variable:
```bash
export RESEMBLE_API_KEY="your_api_key_here"