POST
/
TextToSpeech
Convert text to speech using a specified voice
curl --request POST \
  --url https://api.musicgpt.com/api/public/v1/TextToSpeech \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "text": "<string>",
  "voice_id": "<string>",
  "gender": "<string>",
  "sample_audio_url": "<string>",
  "webhook_url": "<string>"
}'
{
  "success": true,
  "task_id": "72eed5b0-8652-4bb4-9a95-eb0ad4850f12",
  "conversion_id": "648a6823-b2a4-47b3-801e-f452c567ae6f",
  "eta": 19
}
Convert any given text into realistic speech using your chosen voice and gender. TextToSpeech enables you to instantly bring written content to life. Perfect for:
  • 🔈 Creating dynamic audio narrations or voiceovers
  • 🧑‍💼 Choosing gender-specific voice stylings for different contexts
  • 🔁 Using webhooks for real-time integration with your workflows

​
Endpoint

POST /TextToSpeech
Use this endpoint to initiate a new text-to-speech audio generation.

​
Sample Output

Prompt: When I think of superheroes I think of super humans. I think of Superman, Wolverine and Wonder Woman. Usually they have a cape, or a mask to hide their face just in case. They have X-ray vision and super-human strength. Some can even breathe in outer space. They fly around a while, but always come back to keep our cities safe. They’re here to save humanity from itself. It’s a metaphor for how we look outside ourselves for help, and while the fantasies are fun, I choose to look for me and you. Download Audio

​
Try it Yourself

Visit the TextToSpeech Endpoint Explorer to try your own text samples.
💡 Tip: Set a webhook_url to receive results automatically when your audio is ready.

​
Request Parameters

ParameterTypeRequiredDescription
textStringYesThe text content to convert to speech
voice_idStringOptionalVoice model to apply for synthesis. Either voice_id or sample_audio_url must be provided
sample_audio_urlStringOptionalURL of Voice you want. Either voice_id or sample_audio_url must be provided
genderStringYesGender of the voice (“male”, “female”)
webhook_urlStringNoURL to receive a callback with generated audio
Note: You must provide either voice_id or audio_url — not both as None.

​
Sample Request

​
Python

import requests

url = 'https://api.musicgpt.com/api/public/v1/TextToSpeech'
api_key = '<api_key>'

headers = {
    "accept": "application/json",
    "Authorization": api_key,
    "Content-Type": "application/json"
}

data = {
    'text': "The character Sherlock Holmes first appeared in print in 1887's A Study in Scarlet...",
    'voice_id': 'Drake',
    'gender': 'string',
    'webhook_url': 'http://abc.requestcatcher.com/test'
}

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

​
Sample Response

​
Success (200 OK)

{
  "success":true,
  "task_id":"0a65cbb6-2ab8-4949-9ee0-0e8c138ac2cf",
  "conversion_id":"6542baa6-d61f-4d90-b832-ed929d9c0996",
  "eta":17,
  "credit_estimate":0.68,
  "message":"",
  "status":"IN_QUEUE"
}

​
Webhook Response

Once audio is ready, your webhook will receive: 
{
  "success": true, 
  "conversion_type": "Text To Speech", 
  "task_id": "037a9a09-3fc6-4a90-8748-d3406ff712eb", 
  "conversion_id": "f1970224-ab06-4aa6-a832-0f3fd23212b7", 
  "audio_url": "https://lalals.s3.amazonaws.com/projects/f1970224-ab06-4aa6-a832-0f3fd23212b7.mp3", 
  "audio_url_wav": "https://lalals.s3.amazonaws.com/projects/f1970224-ab06-4aa6-a832-0f3fd23212b7.wav", 
  "conversion_cost": "0.68", 
  "conversion_duration": 27.78
}
🎧 Use the audio_url to listen or download your synthesized speech.

​
Error Codes

  • 402 Payment Required: Not enough credits to process the request
  • 422 Unprocessable Entity: Invalid or missing fields
  • 500 Internal Server Error: Server-side failure during processing

​
Payload and Request Formation

Authorizations

​
Authorization
string
header
required

Body

application/json
​
text
string
required

Text to convert to speech

​
sample_audio_url
string
required

An audio URL containing a voice sample of the target speaker without music or overlapping voices. Recommended over voice_id for better output quality.

​
voice_id
string

Voice model ID

​
gender
string

Gender preference for the voice (e.g., "male", "female")

​
webhook_url
string

Callback URL for async processing

Response

Successfully initiated TTS conversion

​
success
boolean
​
task_id
string
​
conversion_id
string
​
eta
integer