Fish Voice Generation API

Fish Audio text-to-speech and voice-cloning service: synthesize speech from text and create custom voice models from reference audio.

API home page: Ace Data Cloud - Fish Voice Generation

Keywords: fish-api, fish-audio, text-to-speech, tts, voice-clone, voice-model, speech-synthesis, rest-api, ai-api, AI API, REST API, Developer API, Ace Data Cloud

Why Use Fish Voice Generation on Ace Data Cloud

• Unified developer platform with one API key, billing system, and usage tracking
• Production-ready AI API endpoints served from https://api.acedata.cloud
• English integration guides, API references, and service documentation
• Global-ready workflow for developers building chat, image, video, music, and search products

Overview

The Fish TTS API converts text into natural speech using a saved voice model or a one-shot HTTPS reference audio sample. The Fish Model APIs create, query, and fetch custom voice models from reference audio, and the Fish Tasks API polls asynchronous jobs.

Application Process

To use the Fish TTS API, apply for the corresponding service on the Fish TTS API page. After entering the page, click the "Acquire" button.

There is a free quota available for first-time applicants, allowing you to use this API for free.

Quick Start

• Base URL: https://api.acedata.cloud
• Service page: Fish Voice Generation on Ace Data Cloud
• Docs: Developer documentation

curl --request POST "https://api.acedata.cloud/fish/tts" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "text": "Hello, this is a demonstration of AI voice synthesis."
  }'

One-shot voice clone

curl --request POST "https://api.acedata.cloud/fish/tts" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --header "model: s2-pro" \
  --data '{
    "text": "New speech in the referenced voice.",
    "format": "mp3",
    "references": [{
      "audio": "https://cdn.acedata.cloud/reference.mp3",
      "text": "The exact reference transcript."
    }]
  }'

This conditions only the current request. Use reference_id for a saved/public voice; never combine it with references.

APIs and Guides

API	Path	Integration Guidance
Fish TTS API	/fish/tts	Fish TTS API Integration Guide
Fish Tasks API	/fish/tasks	Fish Tasks API Integration Guide
Fish Model Create API	/fish/model	Create a custom voice model from reference audio
Fish Model Query API	/fish/model	List voice models
Fish Model Get API	/fish/model/{id}	Fetch a single voice model

Related Resources

• Ace Data Cloud Developer Platform
• Ace Data Cloud Docs
• Status Page
• Ace Data Cloud GitHub Organization

Support

If you meet any issue, please check support info or browse the latest documentation on docs.acedata.cloud