NuLayersNuLayers
Back to Tools

Speech to Text

AI

Transcribe audio files to text using Whisper, Deepgram, or AssemblyAI. Supports 50+ languages.

Available Actions
transcribetranslatediarize
Input Schema
{
  "type": "object",
  "required": [
    "audio_url"
  ],
  "properties": {
    "model": {
      "type": "string"
    },
    "language": {
      "type": "string"
    },
    "audio_url": {
      "type": "string"
    }
  }
}
Output Schema
{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "duration": {
      "type": "number"
    },
    "segments": {
      "type": "array"
    }
  }
}
Quick Start

API Endpoint

POST /api/execute/speech-to-text

cURL Example

curl -X POST \
  https://api.nulayers.com/execute/speech-to-text \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"action": "transcribe"}'
Integration

Get your API key from the dashboard to start using this tool in your AI applications.