Home › Models › MiniMax Speech 2.8 Turbo
MiniMax · Speech 2.8 Turbo · Just Added

MiniMax Speech 2.8 Turbo API

The fast, low-latency tier of MiniMax Speech 2.8 — built for realtime and streaming voice applications, exposed through NovAI's OpenAI-compatible /v1/audio/speech endpoint and billed by real token usage.

$1.54 / 1M
Token rate
≈$0.031
Per 1K chars (ref)
Turbo
Low latency
$0
Platform fee
Sign Up - Get $2.00 Free Credit See All Pricing

Why use MiniMax Speech 2.8 Turbo on NovAI?

  • Low latency - optimized for realtime and conversational voice
  • Cost-efficient - fewer tokens per character than the HD tier
  • Streaming friendly - fast first-byte for live apps
  • URL or binary - response_format=url for a link, mp3/wav/opus for bytes
  • Fine-grained control - speed, volume, pitch and emotion parameters
  • Token billing - pay only for real upstream token usage

Best use cases

  • Realtime voice agents and chatbots
  • Live narration and streaming TTS
  • In-app voice feedback
  • High-volume low-cost synthesis
  • Interactive voice response (IVR)

Quick start

cURL — return an audio URL

curl https://aiapi-pro.com/v1/audio/speech \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-speech-2.8-turbo",
    "input": "Hello! Welcome to NovAI - one API key for every Chinese frontier model.",
    "voice": "male-qn-qingse",
    "response_format": "url"
  }'

Python (OpenAI SDK) — binary audio bytes

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.audio.speech.create(
    model="minimax-speech-2.8-turbo",
    voice="male-qn-qingse",
    input="Hello! Welcome to NovAI - one API key for every Chinese frontier model.",
)
resp.stream_to_file("speech.mp3")

Billed by real upstream token usage (usage.total_tokens × $1.54 / 1M). Set response_format to mp3/wav/opus… for binary bytes (default), or url for a JSON body with audio_url (valid ~24h). Optional: speed, volume, pitch, emotion; default voice male-qn-qingse.

Try MiniMax Speech 2.8 Turbo today

Zero platform fee. Credits never expire. OpenAI-compatible API.

Sign Up Free