skills.rest
AceDataCloud
AceDataCloudOFFICIAL
Explore all skills by this author →
Website𝕏@acedatacloudGitHub

fish-audio

Generate AI audio and clone voices via the Fish Audio API.

13|1|Updated Mar 22, 2026
Search Tags:#text-to-speech#webhook#tts#voice cloning#voice synthesis#async tasks#ai audio
One-click install
npx skills add https://github.com/AceDataCloud/Skills --skill fish-audio-acedatacloud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fish-audio
Source: https://github.com/AceDataCloud/Skills/tree/main/skills/fish-audio
Command: npx skills add https://github.com/AceDataCloud/Skills --skill fish-audio-acedatacloud

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fish Audio helps you turn text into high-quality speech and create custom cloned voices, avoiding the time and cost of traditional voice recording.

Core Features & Use Cases

  • Text-to-Speech Audio Generation: Convert prompts into spoken audio using selectable voice models.
  • Voice Cloning Workflows: Register a reference voice to produce a reusable voice_id for later synthesis.
  • Async Task Support: Generate audio via tasks when long-running processing is needed (polling or callback-based delivery).
  • Use Case: You can transform a script into narration for a product video, then switch to a cloned speaker for consistent branding across all episodes.

Quick Start

Generate spoken audio from text by sending a POST request to /fish/audios with your prompt and an optional voice_id using your AceDataCloud API token.

Frequently Asked Questions about fish-audio

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI audio from text using a voice clone?▼

To generate ai audio from text, send a POST request to the /fish/audios endpoint with your prompt and an optional voice_id from a registered voice clone using your AceDataCloud API token.

What is voice cloning and how does voice synthesis work here?▼

Voice cloning registers a reference voice via a voice_url to produce a reusable voice_id, enabling consistent voice synthesis across multiple text-to-speech audio generation requests without traditional recording.

Do I need an AceDataCloud API token to use text-to-speech and async tasks?▼

Yes, you need an ACEDATACLOUD_API_TOKEN for bearer authentication to handle text-to-speech, voice cloning, and async task polling across the /fish/audios, /fish/voices, and /fish/tasks endpoints.

How do I handle long-running text-to-speech generation jobs?▼

For long-running text-to-speech generation jobs, use asynchronous task support by polling the /fish/tasks endpoint for task status or specifying a callback_url for callback-based audio delivery.

Can I use webhook callbacks for async voice synthesis tasks?▼

Yes, you can use webhook callbacks for async voice synthesis tasks by providing a callback_url in your request, which delivers the final ai audio output automatically once processing completes.

Best way to create a reusable voice_id for product video narration?▼

The best way to create a reusable voice_id for narration is registering a reference voice via the /fish/voices endpoint using a voice_url, ensuring consistent branding across all generated text-to-speech audio.

Related Skills

Explore More Content & Communication Skills→
tony2015116tony2015116

mm-voice-maker

Synthesize and clone voices with MiniMax Voice API and FFmpeg.

Community
Advanced
ldmrepoldmrepo
3

meditation

Generate personalized meditation scripts and TTS audio in selectable durations.

Community
Intermediate
twjarviszyra-webtwjarviszyra-web
3

inference-sh-cli

Search and run inference.sh cloud AI apps with JSON inputs.

Community
Intermediate
hung-phanhung-phan
1

audio

Generate text-to-speech audio and clone voices with specified output files.

Community
Advanced