fish-audio
Generate narration with Fish Audio
Creating multilingual narration requires a text-to-speech service and a suitable public reference voice. This skill guides Claude, Codex, and Claude Code through Fish Audio requests and voice selection.
自分のエージェントでインストール
このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。
Review the Skillstore skill "fish-audio" from https://skillstore.io/skills/acedatacloud-fish-audio.md and its manifest at https://skillstore.io/api/skills/acedatacloud-fish-audio/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。
エージェントが読めるリソース
AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。
テストする
「fish-audio」を使用しています。 Create an MP3 voiceover request for a welcome message.
期待される結果:
- A Fish Audio TTS request with the s2-pro model header.
- The request includes the welcome text, a public reference ID, and MP3 format.
- A reminder to use the configured API token.
「fish-audio」を使用しています。 Find a public voice named Marcus.
期待される結果:
- A model catalog request filtered by the title Marcus.
- Instructions to select an item ID from the public response.
- A follow-up TTS request using that ID as the reference ID.
セキュリティ監査
安全All 46 static alerts are false positives caused by Markdown code formatting, documentation links, and expected API examples. The skill documents authorized text-to-speech requests and public voice browsing; no prompt injection, secret exfiltration, or hidden execution behavior was found.
リスク要因
⚙️ 外部コマンド (38)
🌐 ネットワークアクセス (5)
📁 ファイルシステムへのアクセス (2)
このレポートを共有・引用
バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。
レポートリンクをコピー
https://skillstore.io/skills/acedatacloud-fish-audio/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdownバッジ
[](https://skillstore.io/skills/acedatacloud-fish-audio?utm_source=security_passport_badge)HTMLバッジ
<a href="https://skillstore.io/skills/acedatacloud-fish-audio?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/acedatacloud-fish-audio/security.svg" alt="Skillstore security assessment" loading="lazy"></a>埋め込みカード
<iframe src="https://skillstore.io/embed/skills/acedatacloud-fish-audio.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>学術引用 (APA · BibTeX · CFF)
APA形式の引用
acedatacloud. (2026). fish-audio security audit report (audit version 1) [Author version 1.1]. Skillstore. https://skillstore.io/skills/acedatacloud-fish-audio/audits/1BibTeX形式の引用
@techreport{acedatacloud-acedatacloud-fish-audio-2026,
author = {acedatacloud},
title = {fish-audio security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/acedatacloud-fish-audio/audits/1},
note = {Author version 1.1}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "fish-audio security audit report (audit version 1)"
version: "1.1"
type: report
authors:
- name: "acedatacloud"
date-released: "2026-07-20"
url: "https://skillstore.io/skills/acedatacloud-fish-audio/audits/1"
identifiers:
- type: other
value: "skillstore:acedatacloud-fish-audio:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore スコア
このスコアの理由 証拠の信頼度: 中作成できるもの
Produce product narration
Create a short voiceover request for a product demonstration and choose MP3 output.
Localize training audio
Generate narration for multilingual training material with a suitable public reference voice.
Prototype audio features
Prepare synchronous or asynchronous Fish Audio requests while testing an application workflow.
これらのプロンプトを試す
Create a Fish Audio request for this narration text: [text]. Use MP3 output and explain the required authentication header.
Show how to search the Fish Audio public voice catalog for a voice titled [name]. Explain how to use the returned reference ID.
Create a Fish Audio TTS request for [text] using [model]. Set [format], [sample rate], and a balanced latency mode.
Prepare an asynchronous Fish Audio narration request for [text]. Include a user-controlled callback URL and explain how to poll the task status.
ベストプラクティス
- Keep API tokens in environment configuration and never place real tokens in prompts or source files.
- Use only public reference voices that you are authorized to use.
- Review narration text before submission and avoid sending sensitive information to external services.
回避
- Do not use voice IDs from undocumented endpoints or assume voice-cloning support.
- Do not send API tokens in a request body or publish them in examples.
- Do not use an untrusted callback URL for asynchronous jobs.
よくある質問
What does this skill create?
Which tools can use this skill?
What credential is required?
Can I browse voices?
Which audio formats are supported?
Does the skill clone voices?
開発者情報
作成者
acedatacloudライセンス
Apache-2.0
作者バージョン
v1.1
Skillstore リビジョン
r1
バージョンに関する注意
作者が宣言したバージョンは有効な SemVer ではありません。
参照
6280d196866ca65f09f4edc1c22c832989feb3ea
メンテナンスの新しさ
2026/7/20
利用状況
0 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md