ϟDomestic Models MiniMax Releases M3.1 Flash: 3x Performance Boost, 70% Cost Reduction Learn MoreϟDomestic Models Kimi K3 Released and API Opened Read More →✦New Model Launch Wan3.0 Released View Now →✦New Model Launch DeepSeek V4.1 Flash: Native Multimodal, Outperforms V4 Pro with Lower API Pricing View Details✦New Model Online Seedance 2.5 Release Details View Now →ϟDomestic Models MiniMax Releases M3.1 Flash: 3x Performance Boost, 70% Cost Reduction Learn More
AGTCloud
Contact us Careers
Speechspeech-2.6-turbo
MiniMax · Speech

Speech-2.6-Turbo is a low-latency MiniMax text-to-speech model that combines natural speech quality with faster and more cost-efficient generation for voice chat, agents, and digital-human scenarios.

Overview

Modalities
ReleasedOct 29, 2025

Pricing

Availability

Service statusPast 24 hours

Parameters

Model / versionspeech-2.6-turbo
Input modalitiesText
Output modalitiesSpeech
Sampling parameters—

Example request

curl "https://api.agtcloud.cn/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "speech-2.6-turbo",
    "input": "Today is a wonderful day to build something people love.",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output speech.mp3

Available endpoints

ttsPOST /v1/audio/speechAPI reference

Synthesizes audio from input text and returns an audio file

EXPLORE MODELS

More Speech

Compare capabilities, context and price across models of the same type.

Browse all
MiniMax

speech-2.8-hd is a model from MiniMax for text generation, reasoning, and assistant workflows.

Input / Output · per 1M tokensFrom ¥350 / ¥350
View model
MiniMax

speech-2.8-turbo is a model from MiniMax for text generation, reasoning, and assistant workflows.

Input / Output · per 1M tokensFrom ¥199.9998 / ¥199.9998
View model
MiniMax

speech-2.6-hd is a model from MiniMax for text generation, reasoning, and assistant workflows.

Input / Output · per 1M tokensFrom ¥350 / ¥350
View model
MiniMax

Speech-02-HD is a high-fidelity MiniMax text-to-speech model with strong prosody and stability, high voice-cloning similarity, expressive emotion, and multilingual speech generation.

Input / Output · per 1M tokensFrom ¥350 / ¥350
View model
MiniMax

Speech-02-Turbo is a low-latency MiniMax text-to-speech model with stable prosody, expressive speech, enhanced multilingual capabilities, and efficient real-time generation.

Input / Output · per 1M tokensFrom ¥199.9998 / ¥199.9998
View model