Speech-To-Text API Reference

This page covers all steps to integrate speech-to-text (STT) API into your system.

Good to know: A quick start guide can be good to help folks get up and running with your API in a few steps. Some people prefer diving in with the basics rather than meticulously reading every page of documentation!

Get your API keys

Your API requests are authenticated using API keys. Any request that doesn't include an API key will return an error.

You can generate an API key from your user dashboard in Miragic website anytime.

Authentication

All requests must include the X-API-Key header containing your assigned API key.

curl -X POST "https://backend.miragic.ai/api/v1/speech-to-text/generate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "questiion=Transcribe this audio:" \
  -F "audio_format=mp3" \
  -F "file=@path/to/audio"

import fs from "fs";
import FormData from "form-data";
import fetch from "node-fetch";

const apiKey = "YOUR_API_KEY";
const baseUrl = "https://backend.miragic.ai";

async function stt() {
  const url = `${baseUrl}/api/v1/speech-to-text/generate`;

  const formData = new FormData();
  formData.append("question", "Transcribe this audio:");
  formData.append("audio_format", "mp3");
  formData.append("file", fs.createReadStream("path/to/audio.mp3"));

  const response = await fetch(url, {
    method: "POST",
    headers: {
      "X-API-Key": apiKey,
      ...formData.getHeaders(),
    },
    body: formData,
  });

  const result = await response.text();
  console.log(result);
}

stt();

import requests
import time

api_key = 'YOUR_API_KEY'   # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def stt():
    url = f'{base_url}/api/v1/speech-to-text/generate'
    data = {
        'question': 'Transcribe this audio:', # text to specify output,
        'audio_format': 'mp3' # 'mp3', 'wav'
    }
 
    files=[('file', ('audio.mp3', open('path/to/audio.mp3', 'rb'), 'audio/mpeg'))]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)

if __name__ == '__main__':
    stt()

How To Create Image Generation Task

POST /api/v1/speech-to-text/generate

This API starts the STT process by creating a task that generates text content from audio file.

Processing Information

Tasks are processed asynchronously in the background
Progress can be monitored using the Get Task Status API
The final result will be text content

Request

Parameter

Type

Required

Description

file

File

Yes

Input audio.

audio_format

String

Yes

This value can be set to mp3, or wav.

question

String

Yes

This value is text to specify output content. default value is Transcribe this audio:

Request Example

curl -X POST "https://backend.miragic.ai/api/v1/speech-to-text/generate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "questiion=Transcribe this audio:" \
  -F "audio_format=mp3" \
  -F "file=@path/to/audio"

import fs from "fs";
import FormData from "form-data";
import fetch from "node-fetch";

const apiKey = "YOUR_API_KEY";
const baseUrl = "https://backend.miragic.ai";

async function stt() {
  const url = `${baseUrl}/api/v1/speech-to-text/generate`;

  const formData = new FormData();
  formData.append("question", "Transcribe this audio:");
  formData.append("audio_format", "mp3");
  formData.append("file", fs.createReadStream("path/to/audio.mp3"));

  const response = await fetch(url, {
    method: "POST",
    headers: {
      "X-API-Key": apiKey,
      ...formData.getHeaders(),
    },
    body: formData,
  });

  const result = await response.text();
  console.log(result);
}

stt();

import requests
import time

api_key = 'YOUR_API_KEY'   # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def stt():
    url = f'{base_url}/api/v1/speech-to-text/generate'
    data = {
        'question': 'Transcribe this audio:', # text to specify output,
        'audio_format': 'mp3' # 'mp3', 'wav'
    }
 
    files=[('file', ('audio.mp3', open('path/to/audio.mp3', 'rb'), 'audio/mpeg'))]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)

if __name__ == '__main__':
    stt()

Response

{"success":true,"data":{"jobId":"d6527af6-9697-4860-b635-b930a441fbf2","status":"PENDING"},"message":"Speech-to-text job created successfully"}

Response Field

Field

Type

Description

jobId

String

A unique identifier used to track task status and retrieve results.

status

String

The initial status will be PENDING. Use the Get Task Status API to track progress.

message

String

To indicates the status of task.

success

Logic

true or false to indicate whether task is successful or not.

How To Get Task Status

GET /api/v1/speech-to-text/jobs/:jobId

This API lets you check the status of a STT task and retrieve the final result. Because the STT process runs asynchronously, you’ll need to poll this endpoint until the task is finished.

Task Status:

Status

Description

Progress

Next Action

PENDING

Task is currently being processed.

0~99%

Continue polling

COMPLETED

Task has finished successfully.

100%

Download result using download_signed_url

FAILED

Task processing failed.

N/A

Check error details and retry if needed

Progress Tracking:

The progress field indicates the percentage of task completion (0-100)
Progress updates are available in real-time during the PENDING state
Progress increases as the AI processes different stages of the try-on task

Polling Guidelines:

Start polling immediately after creating the task
Implement exponential backoff to avoid rate limiting
The download_signed_url is temporary and should be used promptly
Consider implementing a timeout after extended polling

Request:

URL Parameters

Parameter

Type

Required

Description

JobId

String

Yes

This value indicates task ID assigned by requesting STT process API

Request Example

curl -X GET https://backend.miragic.ai/api/v1/speech-to-text/jobs/25331fb2-d0b0-44f6fcc85e3e \
  -H "X-API-Key: YOUR_API_KEY"

const fetch = require("node-fetch"); // for Node.js

const apiKey = "YOUR_API_KEY";
const jobId = "25331fb2-d0b0-44f6fcc85e3e";
const url = `https://backend.miragic.ai/api/v1/speech-to-text/jobs/${jobId}`;

const options = {
  method: "GET",
  headers: {
    "X-API-Key": apiKey
  }
};

fetch(url, options)
  .then(response => response.json())
  .then(data => {
    console.log("Response:", data);
  })
  .catch(error => {
    console.error("Error:", error);
  });

import requests

api_key = "YOUR_API_KEY"
job_id = "25331fb2-d0b0-44f6fcc85e3e"
url = f"https://backend.miragic.ai/api/v1/speech-to-text/jobs/{job_id}"

headers = {
    "X-API-Key": api_key
}

response = requests.get(url, headers=headers)

# Print status code and response JSON
print("Status Code:", response.status_code)
print("Response:", response.json())

Response Example

Completed Status (200):

{'success': True, 'data': {'id': 'd6527af6-9697-4860-b635-b930a441fbf2', 'userId': 'eebf31b5-7bec-445e-8b99-51c0311a389d', 'audioFileName': '3.mp3', 'audioUrl': 'https://backend.miragic.ai/uploads/speechToText/1762344258701-12284807.mp3', 'question': 'Transcribe this audio:', 'audioFormat': 'mp3', 'transcription': "The content provided appears to be audio, and I'm unable to transcribe or process voice recordings. If you have any text-based questions or need assistance, feel free to ask!", 'status': 'COMPLETED', 'errorMessage': None, 'metadata': {'apiResponse': {'success': True, 'transcription': "The content provided appears to be audio, and I'm unable to transcribe or process voice recordings. If you have any text-based questions or need assistance, feel free to ask!"}, 'audioFilePath': '/var/www/html/MiragicAI/backend/uploads/speechToText/1762344258701-12284807.mp3', 'processingTimeMs': 9937}, 'creditsUsed': 2, 'createdAt': '2025-11-05T12:04:18.785Z', 'updatedAt': '2025-11-05T12:04:28.723Z'}}

Response Fields

Field

Type

Description

String

Unique identifier of the task

status

String

Current status of the task (PENDING/COMPLETED/FAILED)

transcription

String

text content from audio file.

createdAt

Number

Unix timestamp when processing is created

userId

String

Unique identifier of the user

Full Code Example

The following code lines are quick example to use our API in multiple languages.

curl -X POST "https://backend.miragic.ai/api/v1/speech-to-text/generate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "questiion=Transcribe this audio:" \
  -F "audio_format=mp3" \
  -F "file=@path/to/audio"

import axios from "axios";
import fs from "fs";
import FormData from "form-data";

const apiKey = "YOUR_API_KEY";
const baseUrl = "https://devapi.miragic.ai";

async function stt() {
  const url = `${baseUrl}/api/v1/speech-to-text/generate`;

  const formData = new FormData();
  formData.append("question", "Transcribe this audio:");
  formData.append("audio_format", "mp3");
  formData.append("file", fs.createReadStream("path/to/audio.mp3"));
    
  const headers = {
    "X-API-Key": apiKey,
    ...form.getHeaders(),
  };

  try {
    // Step 1: Create job
    const response = await axios.post(url, form, { headers });
    console.log(response.data);

    if (response.data.success) {
      const jobId = response.data.data.jobId;
      console.log(`Job ID: ${jobId}`);

      // Step 2: Poll for results
      let status = "PENDING";
      while (status !== "COMPLETED" && status !== "FAILED") {
        await new Promise((r) => setTimeout(r, 2000)); // wait 2 sec
        const result = await axios.get(`${baseUrl}/api/v1/speech-to-text/jobs/${jobId}`, {
          headers: { "X-API-Key": apiKey },
        });

        status = result.data.data.status;

        if (status === "COMPLETED") {
          console.log("Result:", result.data);
          break;
        } else if (status === "FAILED") {
          console.log("Job failed:", result.data);
          break;
        } else {
          console.log(`Current status: ${status}...`);
        }
      }
    } else {
      console.log("Error:", response.data);
    }
  } catch (error) {
    console.error("Request failed:", error.response?.data || error.message);
  }
}

stt();

import requests
import time

api_key = 'YOUR_API_KEY'   # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def stt():
    url = f'{base_url}/api/v1/speech-to-text/generate'
    data = {
        'question': 'Transcribe this audio:', # text to specify output,
        'audio_format': 'mp3' # 'mp3', 'wav'
    }
 
    files=[('file', ('audio.mp3', open('path/to/audio.mp3', 'rb'), 'audio/mpeg'))]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)
        
    if response.json()['success']:
        job_id = response.json()['data']['jobId']
        print(f'Job ID: {job_id}')
        
        # Poll for results
        while True:
            result = requests.get(
                f'{base_url}/api/v1/speech-to-text/jobs/{job_id}',
                headers=headers
            )
            
            if result.json()['data']['status'] == 'COMPLETED':
                print('Result:', result.json())
                break
            elif result.json()['data']['status'] == 'FAILED':
                print('Job failed:', result.json())
                break
            
            time.sleep(2)
    else:
        print('Error:', response.json())

if __name__ == '__main__':
    stt()

PreviousText-To-Speech API Reference

Last updated 2 months ago