ModelInfo
English
All models

speech-02-hd

High-definition speech synthesis (legacy generation).

MiniMaxspeech-02-hd2025-04-02Report incorrect data

Specs

Context
—
Max output
—
Input price
$100/ 1M characters
Output price
—
Released
2025-04-02

Context

Not published

Pricing · USD / 1M characters

Input
$100
Output
—
Cache read
—
Cache write
—

Modalities

Input
Text
Output
Audio

API

API types
audio

Reasoning

Reasoning
No

Info

Status
Active
Released
2025-04-02
Knowledge cutoff
—

Features

Confirmed
streaming
Source · official docsVerified 2026-10-11

How to call

1 provider

minimaxmodel = speech-02-hd

audio
POSThttps://api.minimax.io/v1/t2a_v2

JSON

Standard format
speech-02-hd.json
{
  "id": "speech-02-hd",
  "object": "model",
  "created": 1743552000,
  "owned_by": "minimax",
  "name": "speech-02-hd",
  "api": {
    "types": [
      "audio"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "audio"
    ]
  },
  "reasoning": {
    "supported": false,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_characters",
    "input": 100,
    "output": null,
    "cache_read": null,
    "cache_write": null
  },
  "features": [
    "streaming"
  ],
  "info": {
    "status": "active",
    "release_date": "2025-04-02",
    "knowledge_cutoff": null,
    "description": "High-definition speech synthesis (legacy generation).",
    "docs": "https://platform.minimax.io/docs/api-reference/speech-t2a-http",
    "verified_at": "2026-10-11"
  }
}

Official sources

5