Name: Speech 2.5 HD Preview API
Brand: MiniMax

Overview

What is Speech 2.5 HD Preview API?

The brand new HD model. Ultimate Similarity, Ultra-High Quality - supports synchronous text-to-speech audio generation with superior rhythm and stability.

Technical Specifications
- Supported inputs: Text
- Output: Audio
- Endpoint: /tts

Performance Benchmarks
[embed]

Speech 2.5 HD Preview API Pricing
- Input: $130 / 1M tokens

Where to Use Speech 2.5 HD Preview

Voiceovers and narration
Generate natural speech for videos, courses, and IVR at low per-second cost.

Accessibility and voice agents
Add spoken output to apps, readers, and conversational assistants.

Use cases

Speech 2.5 HD Preview is documented as suited to content creation and media production, where written material is turned into professional audio at scale, including podcast and audiobook work.

It is also documented for global e-commerce and marketing, where localized marketing content, product descriptions, and promotional materials are generated in multiple languages while maintaining brand voice consistency.

It is documented for voice agents and IVR systems, with low-latency streaming intended to support conversational customer interactions that sound natural.

It is documented for dubbing and localization, especially when maintaining a speaker’s vocal identity across languages through cross-lingual voice cloning.

How to use Speech 2.5 HD Preview API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to minimax/speech-2.5-hd-preview.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/tts",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "minimax/speech-2.5-hd-preview",
      "text": "Hello from AI/ML API"
    },
)
print(r.json()["audio"])  # URL to the generated audio

const r = 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-2.5-hd-preview",
    "text": "Hello from AI/ML API"
  }),
});
const { audio } = await r.json();
console.log(audio); // URL to the generated audio

curl -X POST https://api.aimlapi.com/v1/tts \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/speech-2.5-hd-preview","text":"Hello from AI/ML API"}'

# the JSON response contains "audio" — a URL to the generated speech

OpenAI-compatible — swap the base URL and it works with your existing SDK.