# MiniMax Speech 2.8 HD — Atlas Cloud API

> MiniMax's latest high-fidelity text-to-speech model: natural, expressive speech in 40 languages with inline interjection tags such as (laughs) and (sighs), emotion control, and selectable voices.

This is the machine-readable API reference for **MiniMax Speech 2.8 HD** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `minimax/speech-2.8-hd`
- **Built by**: MiniMax
- **Modality**: Audio
- **Model page**: https://www.atlascloud.ai/models/minimax/speech-2.8-hd
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.07 per 1K characters
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_audio` with `model: "minimax/speech-2.8-hd"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas models get minimax/speech-2.8-hd --json
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateAudio` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `minimax/speech-2.8-hd`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"minimax/speech-2.8-hd"`
  - Options: "minimax/speech-2.8-hd"

- **`text`** (`string`, _required_):
  Text to synthesize into speech audio. Maximum 10,000 characters per request. Supports interjection tags such as (laughs), (chuckle), (sighs), (breath), (coughs), (gasps) and (humming), and pause markers such as <#0.5#> (seconds).
  - Default: `"Welcome to Atlas Cloud (laughs) — One API for All Media AI."`

- **`voice`** (`string`, _optional_):
  MiniMax system voice ID.
  - Default: `"English_expressive_narrator"`
  - Options: "English_expressive_narrator", "English_radiant_girl", "English_magnetic_voiced_man", "English_compelling_lady1", "English_Aussie_Bloke", "English_captivating_female1", "English_Upbeat_Woman", "English_Trustworth_Man", "English_CalmWoman", "English_UpsetGirl", "English_Gentle-voiced_man", "English_Whispering_girl", "English_Diligent_Man", "English_Graceful_Lady", "English_ReservedYoungMan"

- **`speed`** (`number`, _optional_):
  Speech speed multiplier.
  - Default: `1`
  - Min: 0.5
  - Max: 2

- **`vol`** (`number`, _optional_):
  Speech volume, greater than 0 up to 10.
  - Default: `1`
  - Min: 0.1
  - Max: 10

- **`pitch`** (`integer`, _optional_):
  Speech pitch adjustment.
  - Default: `0`
  - Min: -12
  - Max: 12

- **`emotion`** (`string`, _optional_):
  Emotion of the speech. auto (default) lets the model pick the most natural emotion from the text.
  - Default: `"auto"`
  - Options: "auto", "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm"

- **`language_boost`** (`string`, _optional_):
  Language hint that improves recognition of the text's language or dialect. auto (default) detects it automatically.
  - Default: `"auto"`
  - Options: "auto", "English", "Chinese", "Chinese,Yue", "Japanese", "Korean", "Spanish", "French", "Portuguese", "German", "Italian", "Arabic", "Russian", "Turkish", "Dutch", "Ukrainian", "Vietnamese", "Indonesian", "Thai", "Polish", "Romanian", "Greek", "Czech", "Finnish", "Hindi", "Bulgarian", "Danish", "Hebrew", "Malay", "Persian", "Slovak", "Swedish", "Croatian", "Filipino", "Hungarian", "Norwegian", "Slovenian", "Catalan", "Nynorsk", "Tamil", "Afrikaans"

- **`output_format`** (`string`, _optional_):
  Output audio format.
  - Default: `"mp3"`
  - Options: "mp3", "wav", "flac"

- **`sample_rate`** (`integer`, _optional_):
  Output sample rate.
  - Default: `32000`
  - Options: 8000, 16000, 22050, 24000, 32000, 44100

- **`bitrate`** (`integer`, _optional_):
  Output audio bitrate. Applies to mp3 only.
  - Default: `128000`
  - Options: 32000, 64000, 128000, 256000



**Required Parameters Example**:

```json
{
  "model": "minimax/speech-2.8-hd",
  "text": "Welcome to Atlas Cloud (laughs) — One API for All Media AI."
}
```


**Full Example**:

```json
{
  "model": "minimax/speech-2.8-hd",
  "text": "Welcome to Atlas Cloud (laughs) — One API for All Media AI.",
  "voice": "English_expressive_narrator",
  "speed": 1,
  "vol": 1,
  "pitch": 0,
  "emotion": "auto",
  "language_boost": "auto",
  "output_format": "mp3",
  "sample_rate": 32000,
  "bitrate": 128000
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated audio.

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "id": "",
  "model": "",
  "status": "",
  "outputs": [
    ""
  ],
  "created_at": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateAudio" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/speech-2.8-hd",
  "text": "Welcome to Atlas Cloud (laughs) — One API for All Media AI.",
  "voice": "English_expressive_narrator",
  "speed": 1,
  "vol": 1,
  "pitch": 0,
  "emotion": "auto",
  "language_boost": "auto",
  "output_format": "mp3",
  "sample_rate": 32000,
  "bitrate": 128000
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/minimax/speech-2.8-hd)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### MiniMax Speech 2.8 HD

**MiniMax Speech 2.8 HD** is MiniMax's latest high-fidelity text-to-speech model. It turns text into natural, expressive speech in 40 languages, and you can add laughs, sighs, breaths, and other non-verbal sounds directly in the text.

#### Why Choose This?

- **Studio-grade quality.** HD is tuned for fidelity, so it fits narration, audiobooks, podcasts, and voiceovers.
- **Interjection tags.** Write `(laughs)`, `(chuckle)`, `(sighs)`, `(breath)`, `(coughs)`, `(gasps)`, `(humming)` and more inside `text`, and the voice performs them in place. Speech 2.8 is the first MiniMax version to support this.
- **40 languages.** Set `language_boost` to a specific language or dialect, or leave it on `auto`.
- **Fine control.** Tune `speed`, `vol`, `pitch` and `emotion`, and insert pauses with markers such as `<#0.5#>`.
- **Ready-to-use audio file.** Output is an mp3, wav, or flac file. Billed per 1,000 characters of input text.

#### Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| model | Yes | `minimax/speech-2.8-hd` |
| text | Yes | Text to synthesize, up to 10,000 characters. Supports interjection tags and pause markers. |
| voice | No | Preset voice. Default `English_expressive_narrator`. See the list below. |
| speed | No | Speech speed, 0.5–2.0. Default `1.0`. |
| vol | No | Volume, greater than 0 up to 10. Default `1.0`. |
| pitch | No | Pitch shift, integer -12 to 12. Default `0`. |
| emotion | No | `auto` (default, chosen by the model), `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `calm`. |
| language_boost | No | `auto` (default), `English`, `Chinese`, `Chinese,Yue`, `Japanese`, `Korean`, `Spanish`, `French`, `Portuguese`, `German`, `Italian`, `Arabic`, `Russian`, `Turkish`, `Dutch`, `Ukrainian`, `Vietnamese`, `Indonesian`, `Thai`, `Polish`, `Romanian`, `Greek`, `Czech`, `Finnish`, `Hindi`, `Bulgarian`, `Danish`, `Hebrew`, `Malay`, `Persian`, `Slovak`, `Swedish`, `Croatian`, `Filipino`, `Hungarian`,

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/minimax/speech-2.8-hd · Docs: https://www.atlascloud.ai/docs