Speech to Text (Transcription)

curl --location 'https://api.addisassistant.com/api/v2/stt' \
  --header 'x-api-key: sk_YOUR_KEY' \
  --form 'audio=@"/path/to/voice_note.wav"' \
  --form 'request_data="{ \"language_code\": \"am\" }"'

const formData = new FormData();

// 1. Append the file
// Assuming 'fileInput' is an HTML <input type="file">
formData.append("audio", fileInput.files[0]); 

// 2. Append metadata as a stringified JSON
formData.append("request_data", JSON.stringify({ 
  language_code: "am" 
}));

const response = await fetch("https://api.addisassistant.com/api/v2/stt", {
  method: "POST",
  headers: {
    "x-api-key": "sk_YOUR_KEY"
    // Do NOT set Content-Type header manually for FormData
    // The browser sets it automatically with the boundary
  },
  body: formData
});

const data = await response.json();
console.log("Transcription:", data.data.transcription);

import requests
import json

url = "https://api.addisassistant.com/api/v2/stt"
headers = {"x-api-key": "sk_YOUR_KEY"}

# 1. Prepare Metadata
payload = {
    'request_data': json.dumps({ "language_code": "am" })
}

# 2. Open File
files = [
    ('audio', ('voice.wav', open('/path/to/voice.wav', 'rb'), 'audio/wav'))
]

response = requests.post(url, headers=headers, data=payload, files=files)

print(response.json()['data']['transcription'])