MiniMax Text to Audio

minimax_t2a

MiniMax T2A converts text to natural-sounding speech with multiple voice options and customizable parameters.

Authentication

authorization `string` required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model `string` required

Model ID to use for the request.

Value: minimax_t2a

text `string` required

To Convert as voice Text Content.

output_format `string`

Audio Output Format: url (Return Audio File URL) or hex (Return hexadecimal Audio Data).

Default: url

Options: url, hex

voice_id `string`

Voice ID, such as English_Graceful_Lady, Chinese_Female_01 etc.

speed `number`

Speech rate.

Default: 1.0

Range: 0.5 - 2.0

pitch `integer`

Audio adjust.

Default: 0

Range: -12 - 12

Error Codes

Code	Description
401	API key is missing or invalid
403	Insufficient balance or permission denied
429	Rate limit exceeded
500	Internal server error

Code Examples

curl --location 'https://cloud.vtrix.ai/model/v1/generation' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
  "model": "minimax_t2a",
  "input": [
    {
      "params": {
        "text": "Hello world!",
        "voice_id": "Chinese_Female_01",
        "speed": 1.0
      }
    }
  ]
}'

Response Format

{
  "type": "audio",
  "url": "Generated content URL",
  "jobId": "Job identifier"
}

Authentication

authorization string required

Parameters

model string required

text string required

output_format string

voice_id string

speed number

pitch integer