← 返回 Skills 市场

Fish Audio

Name: Fish Audio
Author: germey

作者 Germey · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

149

总下载

当前安装

版本数

在 OpenClaw 中安装

/install acedatacloud-fish-audio

功能描述

Generate AI audio and synthesize voices with Fish Audio via AceDataCloud API. Use when creating text-to-speech audio, synthesizing voices, or generating audi...

使用说明 (SKILL.md)

Fish Audio — Voice & Audio Synthesis

Generate AI audio and synthesize voices through AceDataCloud's Fish Audio API.

Authentication

export ACEDATACLOUD_API_TOKEN="your-token-here"

Quick Start

curl -X POST https://api.acedata.cloud/fish/audios \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, this is a demonstration of AI voice synthesis."}'

Endpoints

Endpoint	Purpose
`POST /fish/audios`	Generate audio from text or parameters
`POST /fish/voices`	Voice synthesis and cloning
`POST /fish/tasks`	Poll task status

Workflows

1. Text-to-Speech

POST /fish/audios
{
  "text": "The quick brown fox jumps over the lazy dog.",
  "voice_id": "default"
}

2. Voice Synthesis with Custom Voice

POST /fish/voices
{
  "text": "Welcome to our platform.",
  "audio_url": "https://example.com/reference-voice.mp3"
}

Parameters

Parameter	Type	Description
`text`	string	Text to synthesize into speech
`voice_id`	string	Voice model to use
`audio_url`	string	Reference audio for voice cloning
`speed`	number	Speech speed multiplier

Task Polling

POST /fish/tasks
{"task_id": "your-task-id"}

Response

{
  "task_id": "abc123",
  "audio_url": "https://cdn.example.com/output.mp3",
  "success": true
}

Gotchas

Pricing is based on byte count of the generated audio
Voice cloning requires a clear reference audio sample
Text-to-speech supports multiple languages automatically
Use the /fish/voices endpoint for voice cloning workflows

安全使用建议

This skill appears to be a straightforward AceDataCloud TTS integration, but the registry metadata omitted the ACEDATACLOUD_API_TOKEN that SKILL.md instructs you to export. Before installing, verify the vendor and endpoints (api.acedata.cloud) — there is no homepage or source listed. Ask the publisher to update registry metadata to list ACEDATACLOUD_API_TOKEN as the primary credential and to provide a homepage/owner contact. Treat the API token like any secret: ensure it is scoped and revocable, and do not use highly privileged or shared credentials. If you plan to use voice-cloning, be aware it requires uploading or referencing voice samples (privacy/legal considerations). If you cannot confirm the publisher or metadata correction, consider not installing or restrict use to a disposable/scoped token and test in an isolated environment.

功能分析

Type: OpenClaw Skill Name: acedatacloud-fish-audio Version: 1.0.0 The skill bundle is a standard documentation-based integration for the AceDataCloud Fish Audio API. It contains no executable code and the instructions in SKILL.md are limited to legitimate API usage for text-to-speech and voice synthesis via the api.acedata.cloud endpoint, with no evidence of malicious intent, data exfiltration, or prompt injection.

能力评估

ℹ Purpose & Capability

The name/description (Fish Audio, AceDataCloud TTS/voice synthesis) align with the instructions and endpoints in SKILL.md. The required functionality (POST /fish/audios, /fish/voices, task polling) is consistent with a text-to-speech/voice-cloning skill.

✓ Instruction Scope

SKILL.md contains only API usage examples and parameters for TTS and voice cloning; it does not instruct the agent to read unrelated files, traverse system paths, or exfiltrate arbitrary data. It does rely on supplying reference audio via an external URL for voice cloning, which is expected for that workflow.

✓ Install Mechanism

There is no install spec and no code files (instruction-only), so nothing will be written to disk by an installer. This is the lowest-risk install mechanism.

⚠ Credentials

SKILL.md clearly requires ACEDATACLOUD_API_TOKEN (example export and Authorization: Bearer usage), but the registry metadata lists no required env vars and no primary credential. That mismatch is disproportionate and ambiguous: the skill needs an API token but does not declare it. Also, source/homepage are missing, so you can't verify the token's required scope or where credentials will be used beyond the documented endpoints.

✓ Persistence & Privilege

The skill is not always-enabled and does not request system persistence or elevated privileges. Autonomous invocation is allowed (platform default) but that alone is not a red flag here.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install acedatacloud-fish-audio
安装完成后，直接呼叫该 Skill 的名称或使用 /acedatacloud-fish-audio 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of the Fish Audio skill for AceDataCloud. - Generate AI audio and synthesize voices from text (TTS) using multiple voice models. - Supports custom voice synthesis and voice cloning via reference audio. - Provides endpoints for generating audio, managing voice models, and polling task status. - Requires ACEDATACLOUD_API_TOKEN for authentication. - Key features: multi-language support, byte-based pricing, and customizable speech speed.

元数据

Slug acedatacloud-fish-audio

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Fish Audio 是什么？

Generate AI audio and synthesize voices with Fish Audio via AceDataCloud API. Use when creating text-to-speech audio, synthesizing voices, or generating audi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 149 次。

如何安装 Fish Audio？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install acedatacloud-fish-audio」即可一键安装，无需额外配置。

Fish Audio 是免费的吗？

是的，Fish Audio 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Fish Audio 支持哪些平台？

Fish Audio 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Fish Audio？

由 Germey（@germey）开发并维护，当前版本 v1.0.0。