Skip to main content
POST
MiniMax Speech 2.6

Headers

Authorization
string

Body

application/json
model
enum<string>
required

Model name. Must be minimax-speech-2-6.

Available options:
minimax-speech-2-6
text
string
required

Text to synthesize. Required. Max 5000 characters. Billing is based on this length.

Required string length: 1 - 5000
voice
string
default:Wise_Woman

Voice id. Optional — defaults to Wise_Woman. Accepts any voice id MiniMax knows: short system voices (Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl), locale-prefixed ones (English_Graceful_Lady, English_radiant_girl, Japanese_Whisper_Belle, Chinese (Mandarin)_Lyrical_Voice, Cantonese_GentleLady), and cloned voice ids (moss_audio_...). A voice the model does not know makes the task fail, and the tokens are refunded automatically.

Maximum string length: 100
custom_callback_url
string<uri>

Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.

Example:

"https://your-server.com/goenhance/callback"

Response

code
integer
required
msg
string
required
data
object
required