Telephony Short - Speech to Text

Convert short telephony audio recordings and brief telecommunication content to accurate text transcriptions with fast processing optimized for short-duration phone calls and voice messages. Perfect for quick customer interactions, voice prompts, and brief phone conversations.

Note: Audio files must first be uploaded using the Asset API before transcription. The audioUrl parameter should contain the path returned from the Asset API upload.

Supported Models

• telephony_short: Optimized for short telephony audio with fast processing for brief telecommunication content

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	<api-key>
Content-Type	application/json

Supported Audio Formats

• MP3 - MPEG Audio Layer III
• WAV - Waveform Audio File Format (common for phone recordings)
• M4A - MPEG-4 Audio
• FLAC - Free Lossless Audio Codec
• MP4 - MPEG-4 Part 14 (audio only)
• WEBM - WebM Audio
• OGG - Ogg Vorbis

Language Support

The API supports various languages including:

• en-US - English (US)
• en-GB - English (UK)
• vi-VN - Vietnamese
• es-ES - Spanish
• fr-FR - French
• de-DE - German
• it-IT - Italian
• pt-PT - Portuguese
• ru-RU - Russian
• ja-JP - Japanese
• ko-KR - Korean
• zh-CN - Chinese (Simplified)
• ar-SA - Arabic

Note: For a complete list of all supported languages and their language codes, please refer to the Google Cloud Text-to-Speech documentation.

Code Example

Parameters

Parameter	Type	Required	Description
type	string	Yes	Feature type, must be "SPEECH_TO_TEXT"
model	string	Yes	Model identifier, use "telephony_short"
promptObject.audioUrl	string	Yes	Path to audio file (uploaded via Asset API)
promptObject.language	string	Yes	Language code for transcription (e.g., "en-US", "vi-VN")

Code Examples

cURL

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "SPEECH_TO_TEXT",
"model": "telephony_short",
"promptObject": {
  "audioUrl": "audios/2025_02_20_16_26_08_652_New_Recording.m4a",
  "language": "en-US"
}
}'

JavaScript

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'SPEECH_TO_TEXT',
  model: 'telephony_short',
  promptObject: {
    audioUrl: 'audios/2025_02_20_16_26_08_652_New_Recording.m4a',
    language: 'en-US'
  }
})
})

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "SPEECH_TO_TEXT",
"model": "telephony_short",
"promptObject": {
  "audioUrl": "audios/2025_02_20_16_26_08_652_New_Recording.m4a",
  "language": "en-US"
}
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

Try the API directly in your browser:

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

AI Model *Telephony Short Model

Audio URL *

Path to the short telephony audio file you want to transcribe (upload via Asset API first)

Language *English (US)English (UK)VietnameseSpanishFrenchGermanItalianPortugueseRussianJapaneseKoreanChinese (Simplified)Arabic

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "SPEECH_TO_TEXT",
  "model": "telephony_short",
  "promptObject": {
    "audioUrl": "audios/2025_02_20_16_26_08_652_New_Recording.m4a",
    "language": "en-US"
  }
}'

Response Format

{
"success": true,
"data": {
  "transcription": "Thank you for calling. How can I help you today? Yes, I need to check my account balance please.",
  "duration": "00:00:45",
  "language": "en-US",
  "confidence": 0.94
}
}

Use Cases

• Quick Customer Inquiries: Transcribe brief customer support interactions
• Voice Prompts: Convert automated phone system prompts to text
• Short Voice Messages: Transcribe brief voicemail messages
• IVR Interactions: Convert interactive voice response recordings
• Quick Confirmations: Transcribe brief confirmation calls
• Voice Commands: Convert telephony-based voice commands to text
• Short Surveys: Transcribe brief phone survey responses
• Appointment Confirmations: Convert short appointment verification calls

Tips for Best Results

1. Upload First: Use the Asset API to upload your short telephony recording before transcription
2. Duration: Optimized for audio files under 2 minutes for fastest processing
3. Audio Quality: Even short calls benefit from clear audio quality
4. Language Selection: Choose the correct language for optimal accuracy
5. Processing Speed: Short telephony audio processes very quickly
6. Format: Common telephony formats like WAV and MP3 work best

Error Handling

Common error scenarios and solutions:

• File not found: Ensure the audio file was uploaded via Asset API first
• Invalid audioUrl: Verify the path matches exactly what was returned from Asset API upload
• Language not supported: Check that the language code is in the supported list
• Audio too long: Consider using the regular telephony model for longer calls

Response