ConvertOnline

Menu

1. Convert Online
2. Audio Converters
3. AUDIO to TEXT

{
  "convert": "audio-text",
  "multiple": true,
  "from": "audio",
  "to": "text",
  "controls": [
    {
      "type": "dropdown",
      "name": "transcript_format",
      "label": "Transcript Format",
      "options": [
        {
          "label": "Plain Text (.txt)",
          "value": "txt"
        },
        {
          "label": "SubRip (.srt)",
          "value": "srt"
        },
        {
          "label": "WebVTT (.vtt)",
          "value": "vtt"
        },
        {
          "label": "JSON (.json)",
          "value": "json"
        }
      ],
      "defaultValue": "txt",
      "desc": "Choose the output format for each transcript file."
    },
    {
      "type": "dropdown",
      "name": "model",
      "label": "Model",
      "options": [
        {
          "label": "Base (fast, lightweight)",
          "value": "base"
        },
        {
          "label": "Small (better quality)",
          "value": "small"
        },
        {
          "label": "Medium (high quality)",
          "value": "medium"
        },
        {
          "label": "Large (best quality, slowest)",
          "value": "large-v3"
        }
      ],
      "defaultValue": "small",
      "desc": "Select the speech recognition model. Larger models are slower but more accurate."
    },
    {
      "type": "dropdown",
      "name": "language",
      "label": "Language",
      "options": [
        {
          "label": "Auto Detect",
          "value": "auto"
        },
        {
          "label": "English (en)",
          "value": "en"
        },
        {
          "label": "Spanish (es)",
          "value": "es"
        },
        {
          "label": "French (fr)",
          "value": "fr"
        },
        {
          "label": "German (de)",
          "value": "de"
        },
        {
          "label": "Hindi (hi)",
          "value": "hi"
        },
        {
          "label": "Portuguese (pt)",
          "value": "pt"
        },
        {
          "label": "Japanese (ja)",
          "value": "ja"
        },
        {
          "label": "Chinese (zh)",
          "value": "zh"
        }
      ],
      "defaultValue": "auto",
      "desc": "Specify language to improve accuracy, or use Auto Detect."
    },
    {
      "type": "checkbox",
      "name": "translate_to_english",
      "label": "Translate to English",
      "defaultValue": false,
      "desc": "Translates non-English speech to English text (instead of transcribing in the original language)."
    },
    {
      "type": "number",
      "name": "temperature",
      "label": "Sampling Temperature",
      "optional": true,
      "range": {
        "min": 0,
        "max": 1,
        "step": 0.1
      },
      "desc": "Advanced: higher values (e.g., 0.4–0.8) may improve results for difficult audio."
    }
  ],
  "note": "Upload one or more audio files and convert them to text. Each input produces one matching transcript file. For long recordings, accuracy improves with clean audio and a specified language.",
  "type": "audio",
  "operation": "convert"
}