> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax Speech HD

> MiniMax HD voice on Kyma. Multilingual TTS at production quality, ~2.9× cheaper than ElevenLabs Multilingual v2.

## Overview

`minimax-speech-hd` is MiniMax's HD-tier text-to-speech voice. Multilingual, expressive, brand-safe. Right for production narration, audiobooks, multilingual content, and budget-tier brand voice work.

Position it as the production tier between [`minimax-speech-turbo`](/models/minimax-speech-turbo) (bulk / real-time) and [`eleven-multilingual-v2`](/api-reference/audio-speech) (hero brand voice).

## Specs

| Field        | Value                                      |
| ------------ | ------------------------------------------ |
| Model ID     | `minimax-speech-hd`                        |
| Creator      | MiniMax                                    |
| Best for     | Production narration, multilingual content |
| Max input    | 5000 characters per request                |
| Pricing mode | Per character                              |

## Pricing

|                                |    Cost   |
| ------------------------------ | :-------: |
| Per 1K chars                   |  \$0.140  |
| Typical sentence (\~150 chars) | \~\$0.021 |

## Use this when

* You need production-quality voice without ElevenLabs flagship pricing.
* You're shipping multilingual content (29+ languages supported).
* You want a single SKU good enough for narration, not just demos.

## Pick something else when

* You need ultra-low-latency for real-time agents → [`minimax-speech-turbo`](/models/minimax-speech-turbo) (\$0.090/1K char).
* You're cutting hero brand spots and the voice IS the product → [`eleven-multilingual-v2`](/api-reference/audio-speech) (\$0.405/1K char).

## Example

```bash theme={null}
curl -X POST https://kymaapi.com/v1/audio/speech \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-speech-hd",
    "input": "The first move is what sets everything in motion.",
    "voice_id": "male-qn-qingse"
  }' \
  --output speech.mp3
```

## See also

* [`POST /v1/audio/speech`](/api-reference/audio-speech) — endpoint reference
* [`POST /v1/audio/voice-clone`](/api-reference/audio-voice-clone) — clone a custom voice for use here