Speech to Text

Overview

This API provides speech-to-text transcription services, allowing you to convert audio files into text format.

Endpoints

Audio Transcription

Convert audio files to text using speech recognition.

Endpoint: /v1/api/transcribe/
Method: POST
Content-Type: multipart/form-data

API Details

Resource URL	/v1/api/transcribe/
Response Format	JSON
Requires Authentication	No
Rate Limited	Yes
HTTPS	Yes

Request Parameters

Parameter	Description	Required	Type
files	Array of audio files to transcribe	Yes	binary

Example Request

curl -X 'POST' \
  'https://your-api-domain.com/v1/api/transcribe/' \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -F '[email protected]'

Successful Response

{
	"is_error": false,
	"message": "Audio transcription completed successfully",
	"results": {
		"transcription": "This is the transcribed text from the audio file.",
		"confidence": 0.95,
		"duration": "00:01:23",
		"language": "en-US"
	}
}

Error Response

{
	"is_error": true,
	"message": "Validation error occurred",
	"detail": [
		{
			"loc": ["body", "files"],
			"msg": "Field required",
			"type": "value_error.missing"
		}
	]
}

Root Endpoint

Basic endpoint to check API availability.

Endpoint: /
Method: GET