minimax-speech-2-8-turbo

Models/speech-2.8-turbo

Model Code

MiniMax/speech-2.8-turbo

Model overview

Speech synthesis

MiniMax Speech 2.8 Turbo predicts emotion, tone, and related speech attributes from context, and generates natural, high-fidelity, personalized speech for social content, podcasts, audiobooks, news, education, digital humans, and similar scenarios.

Company: MiniMaxProvider: Alibaba Cloud

Model capabilities

Input modalityT

Output modalityT

Model experience✓

Function calling-

Structured output-

Web search-

Prefix completion-

Context cache-

Batch inference-

Fine-tuning-

Model pricing

Voice cloning and voice design$1.48/request

Speech synthesis$0.2985

Rate limits and context

Maximum input length10K

Context length-

Maximum output length-

RPM20

TPM20000

API reference

EndpointPOST /v1/audio/speech

SDKOpenAI-compatible

API code examples

Get API Key

import os
import requests

response = requests.post(
    "https://api.wlrouter.com/v1/audio/speech",
    headers={
        "Authorization": f"Bearer {os.environ['WLROUTER_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
  "model": "MiniMax/speech-2.8-turbo",
  "input": "Hello from WLRouter.",
  "voice": "male-qn-qingse",
  "format": "mp3"
}
)
response.raise_for_status()
print(response.json())