Name: Speech 2.5 Turbo Preview API
Brand: MiniMax

Overview

What is Speech 2.5 Turbo Preview API?

The brand new Turbo model. Ultimate Value, 40 Languages - supports synchronous text-to-speech audio generation with 100+ existing voices and multiple audio specifications.

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

Performance Benchmarks
[embed]

Speech 2.5 Turbo Preview API Pricing
- Input: $78 / 1M tokens

Where to Use Speech 2.5 Turbo 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

Voice and customer support scenarios are documented as fits for this model, including interactive IVR systems, AI receptionists, and automated customer support with low-latency streaming.

Global content creation is another stated use case, with voiceovers for marketing videos, product demos, and advertisements in multiple languages.

E-learning and accessibility are also listed, including narrated course content and converting written material into audio for visually impaired users or audio-first listeners.

Podcasts and audio production are documented too, covering podcast intros, advertisements, and full episodes with consistent voice quality.

How to use Speech 2.5 Turbo Preview API

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

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/tts",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "minimax/speech-2.5-turbo-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-turbo-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-turbo-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.