EchoEntry API Documentation

Getting Started

EchoEntry API converts spoken numbers into accurate digits. Perfect for healthcare apps, warehouse systems, IVR, and any application requiring numeric voice input.

Base URL: https://api.echoentry.ai

Authentication

All API requests require an API key passed in the X-Api-Key header.

# Include this header in every request
X-Api-Key: your_api_key_here
            

Endpoints

POST /v1/transcribe

Transcribe spoken digits from audio to text

Request Parameters

Parameter	Type	Required	Description
`file`	File	Required	Audio file containing spoken digits (WAV, WEBM, MP3, OGG, M4A, FLAC)
`X-Api-Key`	Header	Required	Your API authentication key

Code Examples

cURL

curl -X POST https://api.echoentry.ai/v1/transcribe \ -H "X-Api-Key: your_api_key_here" \ -F "[email protected];type=audio/wav"

curl.exe -X POST https://api.echoentry.ai/v1/transcribe ` -H "X-Api-Key: your_api_key_here" ` -F "[email protected]`;type=audio/wav"

Python

import requests url = "https://api.echoentry.ai/v1/transcribe" headers = { "X-Api-Key": "your_api_key_here" } files = { "file": open("audio.wav", "rb") } response = requests.post(url, headers=headers, files=files) data = response.json() print(data["digits"]) # Output: "123"

JavaScript (Node.js)

Response Format

Success Response (200 OK)

{
  "success": true,
  "filename": "audio.wav",
  "raw_text": "one hundred twenty three",
  "digits": "123",
  "request_id": "",
  "api_key_used": "test_123"
}
                

Field	Type	Description
`success`	Boolean	Whether the transcription was successful
`filename`	String	Original filename of the uploaded audio
`raw_text`	String	Full transcription text before digit extraction
`digits`	String	Extracted digits only (main output)
`request_id`	String	Unique identifier for this request (future use)
`api_key_used`	String	The API key used for this request

Error Responses

401 Unauthorized - Missing API Key

{
  "detail": "Missing X-Api-Key header."
}
                

401 Unauthorized - Invalid API Key

{
  "detail": "Invalid or inactive API key."
}
                

400 Bad Request - Invalid File Format

{
  "detail": "File must be audio format. Accepted extensions: .wav, .webm, .mp3, .ogg, .m4a, .flac"
}
                

500 Internal Server Error - Inference Failed

{
  "detail": "Inference error: [error details]"
}
                

Best Practices

Audio Quality

Sample rate: 16kHz recommended (model is optimized for this)
Format: WAV or WEBM preferred for best quality
Duration: 1-3 seconds optimal (speak number once, then pause)
Background noise: Minimize for best accuracy

Optimal Use Cases

1-3 digit numbers: 95-99% accuracy
4+ digit numbers: Experimental, lower accuracy
Supported accents: US, UK, Irish, Australian, Canadian English

Speaking Tips

Speak clearly and at normal pace
Say number once, then pause
Examples: "forty one" (41), "five sixty four" (564), "one oh five" (105)
For zero: Say "zero" or "oh" interchangeably

Rate Limiting

Current rate limits:

Free tier: 1,000 calls/month
Paid tier: No hard limit (fair use policy applies)

Pricing

Tier	Price	Calls	Features
Free	$0	1,000/month	Full API access, Email support
Pay-as-you-go	$0.01/call	Unlimited	Full API access, Priority support, 99.9% uptime SLA

Support

Need help? Have questions? Contact us:

Email: [email protected]
Response time: Within 24 hours (48 hours on weekends)