This page covers all steps to integrate text-to-speech (TTS) 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.
How To Create Image Generation Task
POST/api/v1/text-to-speech/generate
This API starts the TTS process by creating a task that generates an audio file containing speech.
Processing Information
Tasks are processed asynchronously in the background
Progress can be monitored using the Get Task Status API
The final result will be a high-quality audio
Request
Parameter
Type
Required
Description
text
String
Yes
Input text to generate audio.
voice
String
Yes
This value can be set to alloy, amuch, ash, ballad, dan, echo, onyx, verse, coral, elan, fable, nova, sage, shimmer, etc.
Request Example
Response
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.
success
Logic
true or false to indicate whether task is successful or not.
message
String
To indicate the status of task
How To Get Task Status
GET/api/v1/text-to-speech/jobs/:jobId
This API lets you check the status of a TTS task and retrieve the final result. Because the TTS 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 TTS process API
Request Example
Response Example
Completed Status (200):
Response Fields
Field
Type
Description
id
String
Unique identifier of the task
status
String
Current status of the task (PENDING/COMPLETED/FAILED)
audio_link
String
URL to result audio file.
createdAt
Number
Unix timestamp when processing is created
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/text-to-speech/generate" \
-H "X-API-Key: YOUR_API_KEY" \
-F "text=Say verbatim: A beatiful sunset over the ocean. Where I can make good?" \
-F "voice=alloy"
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 tts() {
const url = `${baseUrl}/api/v1/text-to-speech/generate`;
const formData = new FormData();
formData.append("text", "Say verbatim: A beautiful sunset over the ocean. Where I can make good?");
formData.append("voice", "alloy");
const response = await fetch(url, {
method: "POST",
headers: {
"X-API-Key": apiKey,
...formData.getHeaders(),
},
body: formData,
});
const result = await response.text();
console.log(result);
}
tts();
import requests
import time
api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'
def tts():
url = f'{base_url}/api/v1/text-to-speech/generate'
data = {
'text': 'Say verbatim: A beautiful sunset over the ocean. Where I can make good?',
'voice': 'alloy' # 'alloy', 'amuch', 'ash', 'ballad', 'dan', 'echo', 'onyx', 'verse', 'coral', 'elan', 'fable', 'nova', 'sage', 'shimmer'
}
headers = {'X-API-Key': api_key}
response = requests.request("POST", url, headers=headers, data=data)
print(response.text)
if __name__ == '__main__':
tts()
curl -X POST "https://backend.miragic.ai/api/v1/text-to-speech/generate" \
-H "X-API-Key: YOUR_API_KEY" \
-F "text=Say verbatim: A beatiful sunset over the ocean. Where I can make good?" \
-F "voice=alloy"
import fs from "fs";
import FormData from "form-data";
import fetch from "node-fetch";
const apiKey = "YOUR_API_KEY";
const baseUrl = "https://backend.miragic.ai";
async function tts() {
const url = `${baseUrl}/api/v1/text-to-speech/generate`;
const formData = new FormData();
formData.append("text", "Say verbatim: A beautiful sunset over the ocean. Where I can make good?");
formData.append("voice", "alloy");
const response = await fetch(url, {
method: "POST",
headers: {
"X-API-Key": apiKey,
...formData.getHeaders(),
},
body: formData,
});
const result = await response.text();
console.log(result);
}
tts();
import requests
import time
api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'
def tts():
url = f'{base_url}/api/v1/text-to-speech/generate'
data = {
'text': 'Say verbatim: A beautiful sunset over the ocean. Where I can make good?',
'voice': 'alloy' # 'alloy', 'amuch', 'ash', 'ballad', 'dan', 'echo', 'onyx', 'verse', 'coral', 'elan', 'fable', 'nova', 'sage', 'shimmer'
}
headers = {'X-API-Key': api_key}
response = requests.request("POST", url, headers=headers, data=data)
print(response.text)
if __name__ == '__main__':
tts()
{"success":true,"data":{"jobId":"eddb46cf-ca93-4513-a45d-747a9702c446","status":"PENDING"},"message":"Text-to-speech job created successfully"}
Job ID: eddb46cf-ca93-4513-a45d-747a9702c446
curl -X GET https://backend.miragic.ai/api/v1/text-to-speech/jobs/25331fb2-d0b0-44f6fcc85e3e \
-H "X-API-Key: YOUR_API_KEY"
{'success': True, 'data': {'id': 'eddb46cf-ca93-4513-a45d-747a9702c446', 'userId': 'eebf31b5-7bec-445e-8b99-51c0311a389d', 'text': 'Say verbatim: A beautiful sunset over the ocean. Where I can make good?', 'voice': 'alloy', 'audioUrl': 'https://backend.miragic.ai/uploads/textToSpeech/processed/eebf31b5-7bec-445e-8b99-51c0311a389d/7caf97b8-f60f-41f5-9b23-5bccdfca67e2.mp3', 'status': 'COMPLETED', 'errorMessage': None, 'metadata': {'apiResponse': {'success': True, 'audio_link': 'https://www.dropbox.com/scl/fi/pyrh623yt9etrjjeqb9m6/bcfd45b6-17e4-4d78-adeb-1eecddaae0c0.mp3?rlkey=soni37e2h7e1gjip74bfodmjw&raw=1'}, 'localAudioPath': 'uploads/textToSpeech/processed/eebf31b5-7bec-445e-8b99-51c0311a389d/7caf97b8-f60f-41f5-9b23-5bccdfca67e2.mp3', 'processingTimeMs': 7082}, 'creditsUsed': 2, 'createdAt': '2025-11-04T14:58:15.547Z', 'updatedAt': '2025-11-04T14:58:22.630Z'}}
curl -X POST "https://backend.miragic.ai/api/v1/text-to-speech/generate" \
-H "X-API-Key: YOUR_API_KEY" \
-F "text=Say verbatim: A beatiful sunset over the ocean. Where I can make good?" \
-F "voice=alloy"
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 tts() {
const url = `${baseUrl}/api/v1/text-to-speech/generate`;
const formData = new FormData();
formData.append("text", "Say verbatim: A beautiful sunset over the ocean. Where I can make good?");
formData.append("voice", "alloy");
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/text-to-speech/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);
}
}
tts();
import requests
import time
api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'
def tts():
url = f'{base_url}/api/v1/text-to-speech/generate'
data = {
'text': 'Say verbatim: A beautiful sunset over the ocean. Where I can make good?',
'voice': 'alloy' # 'alloy', 'amuch', 'ash', 'ballad', 'dan', 'echo', 'onyx', 'verse', 'coral', 'elan', 'fable', 'nova', 'sage', 'shimmer'
}
headers = {'X-API-Key': api_key}
response = requests.request("POST", url, headers=headers, data=data)
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/text-to-speech/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__':
tts()
