Speech 2.8 Turbo API

Q: What is the Speech 2.8 Turbo model ID?

Use minimax/speech-2.8-turbo as the model parameter. Requests go to https://api.aimlapi.com/v1/tts with your AI/ML API key.

Try this model

MiniMax Speech 2.8, text-to-speech model for generating natural-sounding speech from text. Supports multiple quality modes (turbo and hd) optimized for latency or audio fidelity.

Modalities: TextAudio
Price: $78per generation
Model type: Text to speech
Released: Apr 13, 2026

Speech 2.8 Turbo overview

Speech 2.8 Turbo by MiniMax

It focuses on delivering natural, expressive speech with minimal delay, making it a strong fit for interactive environments where users expect immediate, human-like responses.

Speech 2.8 Turbo specs

Model ID: minimax/speech-2.8-turbo
Developer: MiniMax
Input: Text
Output: Audio
Endpoint: POST https://api.aimlapi.com/v1/tts

What Is Speech 2.8 Turbo API?

MiniMax Speech 2.8 Turbo is a performance-optimized version of the Speech 2.8 model family. Instead of pushing maximum audio fidelity, it prioritizes speed, responsiveness, and stability under load. The result is a model that feels fluid in real-time interactions while still maintaining a convincing level of vocal realism.

Under the hood, it relies on a Transformer-based architecture with a speaker representation layer, allowing it to generate consistent, identity-driven voices and adapt quickly to different speaking styles. This structure also enables zero-shot voice cloning, where a short audio sample is enough to approximate a new voice.

Performance & Architecture

Attribute	Details
Model Type	Autoregressive Transformer
Voice Cloning	Zero-shot (speaker encoder)
Latency	~200–250 ms
Max Input	~10,000 characters
Streaming	Supported
Architecture Enhancements	Flow-VAE decoder for realism

Natural and Continuous Speech

The model is designed to sound natural without slowing systems down. Speech output feels continuous and well-paced, avoiding the robotic cadence typical of older TTS systems. Emotional tone is not an afterthoughtit , can be shaped deliberately, giving the output a sense of intent rather than neutrality.

Zero-Shot Voice Cloning

Voice cloning works without lengthy setup. A short reference clip can be enough to reproduce tone, rhythm, and general vocal character, which is especially useful when consistency across sessions or characters is required.

Multilingual Coverage

Language support extends across dozens of languages and dialects, making the model suitable for products that operate across regions. Instead of treating localization as a separate layer, speech generation can remain unified across different markets.

Control and Customization

MiniMax Speech 2.8 Turbo gives developers precise control over how speech is delivered. Parameters such as speed, pitch, and volume can be adjusted in a predictable way, allowing teams to fine-tune output to match a product’s tone or UX requirements.

Emotion can also be guided directly. Rather than relying on implicit tone, the model supports intentional delivery styles, which is particularly useful in storytelling, guided experiences, or branded voice interactions.

Audio output can be configured in standard formats such as WAV or MP3, with flexibility around sampling and encoding. This makes it easier to integrate the model into different pipelines without additional processing layers.

Use cases

Real-time voice assistants are a documented fit for Speech 2.8 Turbo, especially where low latency and interactive responses matter. It is described as suited to real-time assistants and interactive applications, including live voice-driven experiences.

IVR systems are another documented use case. The model is described as suitable for interactive voice response workflows where responsive, natural-sounding prompts are needed.

High-volume narration is also documented. Sources describe it as suited to large-scale narration workflows and rapid iteration, including bulk audio generation.

Interactive content is listed as a fit as well. The model is described as useful for content that needs fast voice generation during engagement-heavy experiences.

Speech 2.8 Turbo benchmarks by Artificial Analysis

Human-preference results for Speech 2.8 Turbo in speech arena, next to models available on AI/ML API. Data retrieved Nov 3, 2026.

Speech Arena#30 / 1011151Elo · ±10 at 95%AI/ML API price$78USD per generation

Speech Arena

Elo · text-to-speech arena

AI/ML API price

USD per generation

Models on AI/ML API

Arena results for models you can call with the same API key.

Speech Arena

Listeners hear two clips of the same text and choose the more natural one. Speech 2.8 Turbo ranks #30 of 101.

Speech 2.8 Turbo API pricing

Speech 2.8 Turbo pricing in US dollars
Usage	Price	Unit
Speech generation	$78	per generation

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Speech 2.8 Turbo vs other speech models: prices

AI/ML API rates for 5 models, per generation.

AI/ML API prices in USD per generation
Model	Per generation
Speech 2.8 Turbo	$78
MiniMax Speech 2.6 Turbo	$0.078
MiniMax Speech 2.6 HD	$0.13
Inworld TTS-1.5-Mini	$5.25
Inworld TTS-1.5-Max	$10.5

How to use the Speech 2.8 Turbo API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/tts' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/speech-2.8-turbo",
  "text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "minimax/speech-2.8-turbo",
    "text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}

response = requests.post("https://api.aimlapi.com/v1/tts", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "minimax/speech-2.8-turbo",
    "text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

The Most Accurate Speech Models: Pick the Right One
AI News
MiniMax Audio: Voices from China
AI NewsDecember 25, 2024
MAI-Voice-2, MAI-Transcribe 1.5 & MAI-Image 2.5 Guide
AI News

Speech 2.8 Turbo FAQ

What inputs and outputs does Speech 2.8 Turbo support?

Speech 2.8 Turbo takes text as input and returns audio.

When was Speech 2.8 Turbo released?

Speech 2.8 Turbo became available on April 13, 2026.

How much does Speech 2.8 Turbo cost?

Speech 2.8 Turbo is priced at $78 / 1M.

How is Speech 2.8 Turbo billed?

Speech 2.8 Turbo is billed per generation, a fixed charge per output rather than by prompt length.

Who created Speech 2.8 Turbo?

Speech 2.8 Turbo was built by MiniMax.

How do I call Speech 2.8 Turbo on AI/ML API?

Send a request to https://api.aimlapi.com/v1/tts with minimax/speech-2.8-turbo as the model id.

Is Speech 2.8 Turbo available through a single API key?

Yes. Speech 2.8 Turbo is served through AI/ML API, so the same key and endpoint format used for other models applies.

What is the Speech 2.8 Turbo model ID?

Use minimax/speech-2.8-turbo as the model parameter. Requests go to https://api.aimlapi.com/v1/tts with your AI/ML API key.

Start building with Speech 2.8 Turbo

Get API key

Speech 2.8 Turbo API

minimax/speech-2.8-turbo

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/tts' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "minimax/speech-2.8-turbo",
  "text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "minimax/speech-2.8-turbo",
    "text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}

response = requests.post("https://api.aimlapi.com/v1/tts", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "minimax/speech-2.8-turbo",
    "text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Speech 2.8 Turbo API

Speech 2.8 Turbo overview

Speech 2.8 Turbo by MiniMax

Speech 2.8 Turbo specs

What Is Speech 2.8 Turbo API?

Performance & Architecture

Natural and Continuous Speech

Zero-Shot Voice Cloning

Multilingual Coverage

Control and Customization

Use cases

Speech 2.8 Turbo benchmarks by Artificial Analysis

Speech Arena

AI/ML API price

Models on AI/ML API

Speech Arena

Speech 2.8 Turbo API pricing

Speech 2.8 Turbo vs other speech models: prices

How to use the Speech 2.8 Turbo API

Build with your agent

1Get your API key

2Make your first request

Related articles

Speech 2.8 Turbo FAQ

Start building with Speech 2.8 Turbo

Speech 2.8 Turbo API

Build with your agent

1Get your API key

2Make your first request

Speech 2.8 Turbo API

Speech 2.8 Turbo overview

Speech 2.8 Turbo by MiniMax

Speech 2.8 Turbo specs

What Is Speech 2.8 Turbo API?

Performance & Architecture

Natural and Continuous Speech

Zero-Shot Voice Cloning

Multilingual Coverage

Control and Customization

Use cases

Speech Arena

AI/ML API price

Models on AI/ML API

Speech Arena

Speech 2.8 Turbo API pricing

Speech 2.8 Turbo vs other speech models: prices

How to use the Speech 2.8 Turbo API

Build with your agent

1Get your API key

2Make your first request

Models similar to Speech 2.8 Turbo

Speech 2.8 HD

Speech 2.5 HD Preview

Speech 2.5 Turbo Preview

Eleven v4

Eleven v4 Turbo

Deepgram Aura 2

Related articles

The Most Accurate Speech Models: Pick the Right One

MiniMax Audio: Voices from China

MAI-Voice-2, MAI-Transcribe 1.5 & MAI-Image 2.5 Guide

Speech 2.8 Turbo FAQ

Start building with Speech 2.8 Turbo