> ## Documentation Index
> Fetch the complete documentation index at: https://hanabiaiinc-auto-go-api-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview of Fish Audio

> Discover Fish Audio's powerful voice generation platform and what you can build

export const AudioTranscript = ({voices = []}) => {
  const [selectedVoice, setSelectedVoice] = useState(0);
  const [isPlaying, setIsPlaying] = useState(false);
  const [currentTime, setCurrentTime] = useState(0);
  const [duration, setDuration] = useState(0);
  const [isDropdownOpen, setIsDropdownOpen] = useState(false);
  const audioRef = useRef(null);
  const dropdownRef = useRef(null);
  useEffect(() => {
    const audio = audioRef.current;
    if (!audio) return;
    const updateTime = () => setCurrentTime(audio.currentTime);
    const updateDuration = () => setDuration(audio.duration);
    const handleEnded = () => setIsPlaying(false);
    audio.addEventListener('timeupdate', updateTime);
    audio.addEventListener('loadedmetadata', updateDuration);
    audio.addEventListener('ended', handleEnded);
    return () => {
      audio.removeEventListener('timeupdate', updateTime);
      audio.removeEventListener('loadedmetadata', updateDuration);
      audio.removeEventListener('ended', handleEnded);
    };
  }, []);
  useEffect(() => {
    const handleClickOutside = event => {
      if (dropdownRef.current && !dropdownRef.current.contains(event.target)) {
        setIsDropdownOpen(false);
      }
    };
    if (isDropdownOpen) {
      document.addEventListener('mousedown', handleClickOutside);
    }
    return () => {
      document.removeEventListener('mousedown', handleClickOutside);
    };
  }, [isDropdownOpen]);
  useEffect(() => {
    if (audioRef.current) {
      audioRef.current.pause();
      audioRef.current.load();
      setIsPlaying(false);
      setCurrentTime(0);
    }
  }, [selectedVoice]);
  const togglePlay = () => {
    if (isPlaying) {
      audioRef.current.pause();
    } else {
      audioRef.current.play();
    }
    setIsPlaying(!isPlaying);
  };
  const handleProgressChange = e => {
    const newTime = parseFloat(e.target.value);
    audioRef.current.currentTime = newTime;
    setCurrentTime(newTime);
  };
  const formatTime = time => {
    if (isNaN(time)) return '0:00';
    const minutes = Math.floor(time / 60);
    const seconds = Math.floor(time % 60);
    return `${minutes}:${seconds.toString().padStart(2, '0')}`;
  };
  const currentVoice = voices[selectedVoice];
  return <div className="border rounded-lg bg-card border-gray-200 dark:border-gray-800">
      {}
      <div className="grid grid-cols-3 items-center px-3 py-1.5 bg-muted border-b border-gray-200 dark:border-gray-800">
        <span className="text-xs font-medium">Listen to Page</span>

        <span className="text-xs font-semibold text-muted-foreground text-center">Powered by Fish Audio S1</span>

        {voices.length > 1 ? <div className="relative justify-self-end" ref={dropdownRef}>
            <button onClick={() => setIsDropdownOpen(!isDropdownOpen)} className="flex items-center gap-1.5 px-3 py-1 rounded-full bg-muted hover:bg-gray-200 dark:hover:bg-gray-700 transition-all duration-200 cursor-pointer text-xs">
              <span className="text-muted-foreground">Voice:</span>
              <span className="font-medium">{voices[selectedVoice]?.name}</span>
              <svg className={`w-3 h-3 transition-transform duration-200 ${isDropdownOpen ? 'rotate-180' : ''}`} fill="none" stroke="currentColor" viewBox="0 0 24 24">
                <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 9l-7 7-7-7" />
              </svg>
            </button>

            {isDropdownOpen && <div className="absolute right-0 mt-1 w-auto bg-white dark:bg-black border border-gray-200 dark:border-gray-700 rounded-lg overflow-hidden z-50">
                {voices.map((voice, index) => <button key={index} onClick={() => {
    setSelectedVoice(index);
    setIsDropdownOpen(false);
  }} className={`w-full px-3 py-1.5 text-left text-xs hover:bg-gray-100 dark:hover:bg-gray-800 transition-colors flex items-center gap-2 ${index === selectedVoice ? 'bg-gray-100 dark:bg-gray-800 font-medium' : ''}`}>
                    {voice.id && <img src={`https://public-platform.r2.fish.audio/coverimage/${voice.id}`} alt={voice.name} className="w-5 h-5 rounded-full m-0 flex-shrink-0 object-cover" />}
                    <span className="flex-1 whitespace-nowrap">{voice.name}</span>
                  </button>)}
              </div>}
          </div> : <div className="justify-self-end" />}
      </div>

      {}
      <div className="px-3 py-1.5 bg-card">
        <audio ref={audioRef} src={currentVoice?.url} preload="metadata" />

        <div className="flex items-center gap-2">
          {}
          <button onClick={togglePlay} className="flex-shrink-0 w-6 h-6 flex items-center justify-center bg-gray-300 dark:bg-gray-600 text-gray-800 dark:text-gray-200 rounded-full hover:opacity-80 transition-opacity relative overflow-hidden" aria-label={isPlaying ? 'Pause' : 'Play'}>
            <div className="transition-transform duration-300 ease-in-out" style={{
    transform: isPlaying ? 'rotate(180deg)' : 'rotate(0deg)'
  }}>
              {isPlaying ? <svg className="w-3 h-3" fill="currentColor" viewBox="0 0 24 24">
                  <path d="M6 4h4v16H6V4zm8 0h4v16h-4V4z" />
                </svg> : <svg className="w-3 h-3 ml-0.5" fill="currentColor" viewBox="0 0 24 24">
                  <path d="M8 5v14l11-7z" />
                </svg>}
            </div>
          </button>

          {}
          <div className="flex-1 flex items-center gap-2">
            <span className="text-xs font-mono text-gray-500 dark:text-gray-400 min-w-[35px]">
              {formatTime(currentTime)}
            </span>

            <div className="flex-1 relative h-1 bg-gray-200 dark:bg-gray-700 rounded-full overflow-hidden">
              <div className="absolute top-0 left-0 h-full bg-gray-400 dark:bg-gray-500 transition-all duration-100" style={{
    width: `${duration ? currentTime / duration * 100 : 0}%`
  }} />
              <input type="range" min="0" max={duration || 0} value={currentTime} onChange={handleProgressChange} className="absolute top-0 left-0 w-full h-full opacity-0 cursor-pointer" />
            </div>
            <span className="text-xs font-mono text-gray-500 dark:text-gray-400 min-w-[35px]">
              {formatTime(duration)}
            </span>
          </div>
        </div>
      </div>
    </div>;
};

<AudioTranscript
  voices={[
{
  "id": "8ef4a238714b45718ce04243307c57a7",
  "name": "E-girl",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/getting-started-introduction/8ef4a238714b45718ce04243307c57a7.mp3"
},
{
  "id": "802e3bc2b27e49c2995d23ef70e6ac89",
  "name": "Energetic Male",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/getting-started-introduction/802e3bc2b27e49c2995d23ef70e6ac89.mp3"
},
{
  "id": "933563129e564b19a115bedd57b7406a",
  "name": "Sarah",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/getting-started-introduction/933563129e564b19a115bedd57b7406a.mp3"
},
{
  "id": "bf322df2096a46f18c579d0baa36f41d",
  "name": "Adrian",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/getting-started-introduction/bf322df2096a46f18c579d0baa36f41d.mp3"
},
{
  "id": "b347db033a6549378b48d00acb0d06cd",
  "name": "Selene",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/getting-started-introduction/b347db033a6549378b48d00acb0d06cd.mp3"
},
{
  "id": "536d3a5e000945adb7038665781a4aca",
  "name": "Ethan",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/getting-started-introduction/536d3a5e000945adb7038665781a4aca.mp3"
}
]}
/>

## What is Fish Audio?

Fish Audio is a cutting-edge AI platform for voice generation, voice cloning, and audio storytelling.
Our technology brings dynamic, natural-sounding voices to your applications, enabling immersive experiences across industries.

<Tip>
  Introducing our latest generation voice models:

  **Fish Audio S1:** Our latest model delivers unparalleled naturalness and emotion, setting a new standard for AI-generated speech. [Learn more about our models →](/developer-guide/models-pricing/models-overview)
</Tip>

## Core Capabilities

<CardGroup cols={3}>
  <Card title="Text-to-Speech" icon="microphone">
    Generate natural, expressive speech from text in multiple languages and styles
  </Card>

  <Card title="Voice Cloning" icon="copy">
    Create custom voice models from as little as 15 seconds of audio
  </Card>

  <Card title="Audio Storytelling" icon="book-open">
    Build multi-character narratives with emotion and dynamic voice switching
  </Card>
</CardGroup>

## Try It Now

<CardGroup cols={2}>
  <Card title="Explore Voices" icon="wand-magic-sparkles" href="https://fish.audio/discovery">
    Test our voices in the interactive playground - no code required
  </Card>

  <Card title="View Models" icon="layer-group" href="/developer-guide/models-pricing/models-overview">
    Browse available voice models and their capabilities
  </Card>
</CardGroup>

## Ready to Start?

Get your API key and make your first API call in minutes.

<Card title="Quick Start Guide" icon="rocket" href="/developer-guide/getting-started/quickstart">
  Generate your first AI voice in under 5 minutes
</Card>

## Platform Capabilities

Fish Audio empowers developers to create innovative voice experiences across diverse industries. Whether you're building consumer apps, enterprise solutions, or creative tools, our platform provides the flexibility and power you need.

### What You Can Build

<CardGroup cols={3}>
  <Card title="Content Creation" icon="podcast">
    Automate podcast production, YouTube narration, and audiobook generation
  </Card>

  <Card title="Gaming" icon="gamepad">
    Create dynamic NPC dialogue and real-time character voices
  </Card>

  <Card title="Education" icon="graduation-cap">
    Build interactive language learning tools and accessible educational content
  </Card>

  <Card title="Customer Service" icon="headset">
    Deploy natural-sounding IVR systems and support agents
  </Card>

  <Card title="Accessibility" icon="universal-access">
    Develop screen readers and voice restoration tools
  </Card>

  <Card title="Entertainment" icon="music">
    Generate ASMR content, music vocals, interactive stories, and adult content
  </Card>
</CardGroup>

### Key Features

<CardGroup cols={3}>
  <Card title="Ultra-low latency" icon="bolt">
    Stream audio in real-time for live applications
  </Card>

  <Card title="High-quality voices" icon="sparkles">
    Industry-leading naturalness and clarity
  </Card>

  <Card title="Multilingual support" icon="globe">
    Generate speech in 30+ languages
  </Card>

  <Card title="Emotion control" icon="masks-theater">
    Fine-tune prosody, emotion, and speaking style
  </Card>

  <Card title="Simple integration" icon="plug">
    RESTful API with SDKs for Python, Node.js, and more
  </Card>

  <Card title="Scalable" icon="chart-line">
    Handle everything from prototypes to production workloads
  </Card>
</CardGroup>

## Learn More

* [Models & Pricing](/developer-guide/models-pricing/models-overview) - Explore voice models and pricing options
* [Core Features](/developer-guide/core-features/text-to-speech) - Deep dive into TTS and voice cloning
* [SDKs & Tools](/developer-guide/sdk-guide/python/installation) - Install language-specific libraries
* [Best Practices](/developer-guide/best-practices/voice-cloning) - Production-ready tips and optimization for voice cloning, emotion and expression control, and real-time voice streaming