> ## 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.

# Speech to Text

> Convert audio to text with Fish Audio JavaScript SDK

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/javascript-speech-to-text/8ef4a238714b45718ce04243307c57a7.mp3"
},
{
  "id": "802e3bc2b27e49c2995d23ef70e6ac89",
  "name": "Energetic Male",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/javascript-speech-to-text/802e3bc2b27e49c2995d23ef70e6ac89.mp3"
},
{
  "id": "933563129e564b19a115bedd57b7406a",
  "name": "Sarah",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/javascript-speech-to-text/933563129e564b19a115bedd57b7406a.mp3"
},
{
  "id": "bf322df2096a46f18c579d0baa36f41d",
  "name": "Adrian",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/javascript-speech-to-text/bf322df2096a46f18c579d0baa36f41d.mp3"
},
{
  "id": "b347db033a6549378b48d00acb0d06cd",
  "name": "Selene",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/javascript-speech-to-text/b347db033a6549378b48d00acb0d06cd.mp3"
},
{
  "id": "536d3a5e000945adb7038665781a4aca",
  "name": "Ethan",
  "url": "https://pub-b995142090474379a930b856ab79b4d4.r2.dev/audio/javascript-speech-to-text/536d3a5e000945adb7038665781a4aca.mp3"
}
]}
/>

## Prerequisites

<AccordionGroup>
  <Accordion icon="user-plus" title="Create a Fish Audio account">
    Sign up for a free Fish Audio account to get started with our API.

    1. Go to [fish.audio/auth/signup](https://fish.audio/auth/signup)
    2. Fill in your details to create an account, complete steps to verify your account.
    3. Log in to your account and navigate to the [API section](https://fish.audio/app/api-keys)
  </Accordion>

  <Accordion icon="key" title="Get your API key">
    Once you have an account, you'll need an API key to authenticate your requests.

    1. Log in to your [Fish Audio Dashboard](https://fish.audio/app/api-keys/)
    2. Navigate to the API Keys section
    3. Click "Create New Key" and give it a descriptive name, set a expiration if desired
    4. Copy your key and store it securely

    <Warning>Keep your API key secret! Never commit it to version control or share it publicly.</Warning>
  </Accordion>
</AccordionGroup>

## Basic Usage

Transcribe audio to text:

```typescript theme={null}
import { FishAudioClient } from "fish-audio";
import { createReadStream } from "fs";

const fishAudio = new FishAudioClient({ apiKey: process.env.FISH_API_KEY });

const result = await fishAudio.speechToText.convert({
  audio: createReadStream("audio.mp3"),
});

console.log(result.text);
console.log("Duration (s):", result.duration);
```

## Language Specification

Improve accuracy by specifying the language:

```typescript theme={null}
// English transcription
await fishAudio.speechToText.convert({
  audio: createReadStream("audio.mp3"),
  language: "en"
});

// Chinese transcription
await fishAudio.speechToText.convert({
  audio: createReadStream("audio.mp3"),
  language: "zh"
});
```

Common language codes: `en` (English), `zh` (Chinese), `es` (Spanish), `fr` (French), `de` (German), `ja` (Japanese), `ko` (Korean), `pt` (Portuguese)

<Tip>
  Automatic language detection works well, but specifying the language improves accuracy and speed.
</Tip>

## Working with Segments

Get detailed timing for each segment:

```typescript theme={null}
const response = await fishAudio.speechToText.convert({ audio: createReadStream("audio.mp3") });

// Full transcription
console.log(response.text);

// Segment details
for (const seg of response.segments ?? []) {
  console.log(`[${seg.start.toFixed(2)}s - ${seg.end.toFixed(2)}s] ${seg.text}`);
}
```

## Timestamps Control

Control timestamp generation:

```typescript theme={null}
// Include timestamps (default)
await fishAudio.speechToText.convert({ audio: createReadStream("audio.mp3"), ignore_timestamps: false });

// Skip timestamp processing for faster results
await fishAudio.speechToText.convert({ audio: createReadStream("audio.mp3"), ignore_timestamps: true });
```

<Note>
  `ignore_timestamps: false` (default) includes segment timestamps. Set to `true` to skip timestamp processing for faster transcription when you only need the text.
</Note>

## Audio Formats

Supported audio formats:

* MP3 (recommended)
* WAV
* M4A
* OGG
* FLAC
* AAC

File requirements:

* Maximum size: 100MB
* Maximum duration: 60 minutes
* Sample rate: 16kHz or higher recommended

## Transcribing TTS Output

Transcribe generated speech:

```typescript theme={null}
import { FishAudioClient } from "fish-audio";

const fishAudio = new FishAudioClient();

// Generate speech
const ttsAudio = await fishAudio.textToSpeech.convert({ text: "Hello, this is a test" });

// Transcribe it
const asr = await fishAudio.speechToText.convert({ audio: ttsAudio });
console.log(asr.text);
```

## Error Handling

Handle common errors:

```typescript theme={null}
try {
  await fishAudio.speechToText.convert({ audio: createReadStream("audio.mp3") });
} catch (e: any) {
  const status = e?.status || e?.response?.status;
  if (status === 413) console.error("Audio file too large (max 100MB)");
  else if (status === 400) console.error("Invalid audio format");
  else throw e;
}
```

## Response Structure

The ASR response includes:

| Field      | Type          | Description               |
| ---------- | ------------- | ------------------------- |
| `text`     | string        | Complete transcription    |
| `duration` | number        | Audio duration (seconds)  |
| `segments` | ASRSegment\[] | Timestamped text segments |

Segment structure:

| Field   | Type   | Description          |
| ------- | ------ | -------------------- |
| `text`  | string | Segment text         |
| `start` | number | Start time (seconds) |
| `end`   | number | End time (seconds)   |

<Warning>
  Note the timing units: `duration` and segment times are in seconds.
</Warning>

## Request Parameters

| Parameter           | Type    | Description                | Default            |                     |          |
| ------------------- | ------- | -------------------------- | ------------------ | ------------------- | -------- |
| `audio`             | File    | Buffer                     | Readable stream    | Audio to transcribe | Required |
| `language`          | string  | Language code (e.g., "en") | None (auto-detect) |                     |          |
| `ignore_timestamps` | boolean | Skip timestamp processing  | false              |                     |          |