Skip to main content
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>",
  "sample_audio_url": "<string>",
  "voice_id": "<string>",
  "gender": "<string>",
  "webhook_url": "<string>"
}
'
{
  "success": true,
  "task_id": "72eed5b0-8652-4bb4-9a95-eb0ad4850f12",
  "conversion_id": "648a6823-b2a4-47b3-801e-f452c567ae6f",
  "eta": 19
}

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