Speech 2.5 HD Preview API

minimax/speech-2.5-hd-preview
The brand new HD model.
Output
Released
Jan 5, 2026

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.

Speech 2.5 HD Preview API Pricing

TypePrice
Input
$130 / 1M characters
Output

Speech 2.5 HD Preview vs other models

ModelInputOutputContextBest for
$130 / 1M characters
Speech synthesis
$130 / 1M characters
$130 / 1M
Speech synthesis
$130 / 1M characters
$0.13 / 1M tokens
Speech synthesis
$78 / 1M characters
$0.078 / 1M tokens
Speech synthesis
$13 / 1M characters
$0.013 / 1M tokens
Speech synthesis

Frequently asked questions

Speech 2.5 HD Preview takes text as input and returns audio.

Speech 2.5 HD Preview became available on January 5, 2026.

Speech 2.5 HD Preview is priced at input $130 / 1M characters.

Speech 2.5 HD Preview was built by MiniMax.

Send a request to https://api.aimlapi.com/v1/tts with minimax/speech-2.5-hd-preview as the model id.

Yes. Speech 2.5 HD Preview is served through AI/ML API, so the same key and endpoint format used for other models applies.

It is described by MiniMax as an HD model with ultimate similarity and ultra-high quality, offering synchronous text-to-speech generation with strong rhythm and stability.

Start building with Speech 2.5 HD Preview

Get API Key
1000+ models, one API.