Does Fish Audio support long-form audio generation?

Yes, the skill supports asynchronous task polling, allowing you to initiate a request and check the status until the audio is ready.

What models are available for text-to-speech?

The skill supports various models provided by Fish Audio, including 'speech-1.5' and 'speech-1.5-hd' for higher quality output.

How do I authenticate the Fish Audio skill?

You must provide an ACEDATACLOUD_API_TOKEN in your .env file to authorize the skill to communicate with AceDataCloud services.

Can I create a custom voice using this skill?

Yes, you can use the voice cloning feature by providing a reference audio URL to create a unique voice ID for synthesis.

Fish Audio AI

Name: Fish Audio AI
Author: AceDataCloud

byAceDataCloud

•

Ciencia de Datos y ML

Generates realistic AI voice synthesis and custom voice clones using the AceDataCloud API.

The Fish Audio skill enables developers to integrate high-quality text-to-speech and professional voice cloning capabilities directly into their AI-driven workflows. By connecting Claude Code to AceDataCloud's infrastructure, users can synthesize speech from text, register unique voice profiles from audio samples, and manage asynchronous audio generation tasks. This skill is ideal for developers building voice-enabled applications, automated content creation pipelines, or accessibility tools that require natural-sounding AI voices.

Características Principales

01Support for multiple speech models including HD variants

02Automatic multilingual support for global applications

03High-fidelity text-to-speech (TTS) synthesis

04Instant voice cloning from reference audio URLs

05Asynchronous task management for efficient audio processing

065 GitHub stars

Casos de Uso

01Converting text documentation into accessible audio format for users

02Generating automated voiceovers for video tutorials and marketing content

03Creating custom-branded AI voices for virtual assistants and chatbots

Características Principales

01Support for multiple speech models including HD variants

02Automatic multilingual support for global applications

03High-fidelity text-to-speech (TTS) synthesis

04Instant voice cloning from reference audio URLs

05Asynchronous task management for efficient audio processing

065 GitHub stars

Casos de Uso

01Converting text documentation into accessible audio format for users

02Generating automated voiceovers for video tutorials and marketing content

03Creating custom-branded AI voices for virtual assistants and chatbots