Skip to main content

ASR Quickstart

This guide makes your first transcription against Shisa ASR. You will need an API key — create one in the Shisa platform. New accounts include $10 in free credits.

1. Get your API key​

Sign up for a Shisa AI account and obtain your API key from the Shisa platform. Include it in the Authorization header with the shsk: prefix:

Authorization: Bearer YOUR_API_KEY
warning

Shisa API keys start with shsk:. Pass the full key — including the shsk: prefix — in the Authorization: Bearer YOUR_API_KEY header. A missing or malformed token returns a 401 error.

tip

Keep your API key out of source control. Read it from an environment variable (for example SHISA_API_KEY) in real applications.

2. Prepare your audio​

The API accepts base64-encoded audio in WAV, OGG, MP3, or FLAC. Encode any supported file to base64 first:

base64 -w0 audio.ogg    # Linux
base64 -i audio.ogg     # macOS

3. Make a request​

Send a POST request to the endpoint with your base64-encoded audio in the audio field.

curl
curl -s -XPOST 'https://api.shisa.ai/asr/srt/audio_llm' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "audio": "'$(base64 -w0 audio.ogg)'"
  }'
Python
import base64
import requests

# Read and encode audio file
with open("audio.ogg", "rb") as f:
    audio_data = base64.b64encode(f.read()).decode("utf-8")

url = "https://api.shisa.ai/asr/srt/audio_llm"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "audio": audio_data
}

response = requests.post(url, headers=headers, json=payload)
response.raise_for_status()
print(response.json())
JavaScript
async function transcribeAudio(audioFile) {
  // Read file and convert to base64
  const fileBuffer = await audioFile.arrayBuffer();
  const base64Audio = btoa(
    new Uint8Array(fileBuffer).reduce(
      (data, byte) => data + String.fromCharCode(byte),
      ''
    )
  );

  const response = await fetch('https://api.shisa.ai/asr/srt/audio_llm', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      audio: base64Audio
    })
  });

  if (!response.ok) {
    throw new Error(`API request failed: ${response.status}`);
  }

  return await response.json();
}

// Example usage with file input
document.querySelector('#audioInput').addEventListener('change', async (e) => {
  const file = e.target.files[0];
  if (file) {
    const result = await transcribeAudio(file);
    console.log('Transcription:', result);
  }
});
note

Only the audio field is required. Language is auto-detected and tuning parameters use sensible defaults. To target a specific language or add domain terms, see the API reference.

4. Read the response​

The API returns a JSON response with the transcribed text, the detected language, and a confidence score:

{
  "text": "こんにちは、シサAIです。",
  "language": "ja",
  "confidence": 0.98
}

Next steps​