Automatic speech recognition¶

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "file": {
      "description": "Audio file (mp3, wav, m4a, flac, and webm are supported)",
      "type": "string",
      "format": "binary"
    },
    "model": {
      "description": "Model name; defaults to openai/whisper-large-v3",
      "type": "string",
      "default": "openai/whisper-large-v3"
    },
    "temperature": {
      "description": "Sampling temperature (0.0-1.0); defaults to 0.6",
      "type": "string",
      "default": "0.6"
    }
  },
  "required": ["file", "model"]
}

{
  "error": "invalid_request",
  "message": "The audio file is missing or its format is not supported"
}

{
  "error": "unauthorized",
  "message": "Missing or invalid access token"
}

{
  "error": "rate_limit_exceeded",
  "message": "Too many requests; please retry later"
}

curl -X POST 'https://api.atomgit.com/api/v5/audio/transcriptions' \
  -H 'Authorization: Bearer <token>' \
  -F 'file=@<path/to/audio.mp3>' \
  -F 'model=openai/whisper-large-v3' \
  -F 'temperature=0.6'

// Native fetch (Node.js 18+ / browsers)
const form = new FormData();
form.append("file", new Blob([audioBuffer], { type: "audio/mpeg" }), "audio.mp3");
form.append("model", "openai/whisper-large-v3");
form.append("temperature", "0.6");

const response = await fetch("https://api.atomgit.com/api/v5/audio/transcriptions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR-TOKEN>",
  },
  body: form,
});

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

const data = await response.json();
console.log(data);

import requests

resp = requests.post(
    "https://api.atomgit.com/api/v5/audio/transcriptions",
    headers={
        "Authorization": "Bearer <YOUR-TOKEN>",
    },
    files={"file": open("<path/to/audio.mp3>", "rb")},
    data={
        "model": "openai/whisper-large-v3",
        "temperature": "0.6",
    },
    timeout=60,
)
resp.raise_for_status()

print(resp.json())

{
  "text": "Good morning. The weather is lovely today and the sun is shining. I plan to take a walk in the park, grab a cup of coffee, and start my day's work."
}