Audio

MiniMax 2.8 Turbo

MiniMax Speech 2.8 Turbo is the latency-optimized variant of MiniMax's 2.8 speech generation line, tuned for real-time and streaming TTS use cases. It trades some fidelity for fast first-byte response, making it suitable for voice assistants and interactive agents. Use it for live voice interfaces, conversational agents, and any application where speech latency is critical.

Pricing

Input

$60.00 / 1M chars

Output

Pay only for what you use. No subscriptions, no minimums.

Specs

Context
Max output
Latency
Fast
Category
Audio
Arabic
Partial

Constraints & limits

Max input

10,000 chars

Output

MP3 (32 kHz, 128 kbps, mono)

Default voice

Wise_Woman

The gateway auto-clamps requests to the model's limits where possible.

Quick start

This sample hits the text-to-speech endpoint. Change base_url and your key, then run it.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.audio.speech.create(
    model="minimax/minimax-speech-2.8-turbo",
    input="Welcome to Thalam, your unified gateway to AI models.",
)

with open("out.mp3", "wb") as f:
    f.write(response.content)

Similar models

ElevenLabs v3

Audio

ElevenLabs v3: gold-standard voice synthesis.

Context
Max output
Latency
Fast
Input price
$0.120 / min
Output price

ElevenLabs Multilingual v2

Audio

ElevenLabs Multilingual v2: faithful, consistent voice synthesis.

Context
Max output
Latency
Fast
Input price
$0.120 / min
Output price

Fish Audio TTS

Audio

Fish Audio TTS: multilingual voice synthesis with cloning.

Context
Max output
Latency
Fast
Input price
$15.00 / 1M chars
Output price

Featured in

More from MiniMax

All MiniMax models (13)