Name: MiniMax Speech 2.8 HD API: Natural Text to Speech
Brand: magicapi
SKU: api-magicapi-high-fidelity-audio-generation-minimax-speech-2-8-hd
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎙️ Text-to-Speech API (MiniMax Speech 2.8 HD)

## Overview
MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. Its developer describes it as focused on high-fidelity audio, with studio-grade quality, flexible emotion control, multilingual support and support for cloned voices.

Send up to 10,000 characters of `text` and pick a `voice_id`. You can change the `emotion`, `speed`, `pitch` and `volume`, and choose the audio format, sample rate, bitrate and channels. Each request returns the URL of one audio file. You pay per character of input text.

## Features
- **Voices**: any MiniMax system voice (the default is `English_Wiselady`) or the `voice_id` of a cloned MiniMax voice.
- **Emotion control**: `emotion` accepts `auto` (default), `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `calm`, `fluent` or `neutral`.
- **Pauses**: insert markers like `<#0.5#>` in `text` to add a pause of that many seconds.
- **Voice tuning**: `speed` (0.5 to 2), `pitch` (-12 to +12 semitones) and `volume` (0 to 10).
- **Language hint**: `language_boost` lists 41 languages plus `Automatic`; `english_normalization` improves how English numbers and dates are read.
- **Audio formats**: `mp3` (default, 32 to 256 kbps), `wav`, `flac` or `pcm`, at 8000 to 44100 Hz, `mono` or `stereo`.

## Use Cases
1. **Narration**: articles, lessons and audiobook chapters of up to 10,000 characters per request.
2. **Voiceovers**: product videos and explainers with a chosen voice and emotion.
3. **Phone and app prompts**: menu messages at an 8000 or 16000 Hz sample rate.
4. **Multilingual audio**: the same script read in several languages with `language_boost`.

## Visual Examples
### Example Input
Text: "Hello, world! This is a simple test of the MiniMax Speech 2.8 model, now on api.market."

Sent with `voice_id` `Wise_Woman`, `emotion` `auto`, `speed` `1`, `pitch` `0`, `volume` `1`, `audio_format` `mp3` at `128000` bps, `sample_rate` `32000`, `channel` `mono` and `language_boost` `None`.

### Example Output
[Listen to the example output](https://blog.api.market/wp-content/uploads/2026/10/speech-2-8-hd-output-rk13j36v-api-market.mp3)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `text` | string | Yes |  |  | Text to narrate (max 10,000 characters). Use markers like <#0.5#> to insert pauses in seconds |
| `voice_id` | string | No | `English_Wiselady` |  | Voice to synthesize: a MiniMax system voice ID (for example English_Wiselady or English_Deep-VoicedGentleman) or the voice_id of a cloned MiniMax voice |
| `speed` | number | No | `1` | `0.5` to `2` | Speech speed multiplier (0.5 to 2.0). Lower is slower, higher is faster |
| `volume` | number | No | `1` | `0` to `10` | Relative loudness. 1.0 is the default gain. Range 0 to 10 |
| `pitch` | integer | No | `0` | `-12` to `12` | Semitone offset applied to the voice (-12 to +12) |
| `emotion` | string | No | `auto` | `auto`, `happy`, `sad`, `angry`, `fearful`, `disgusted`, `surprised`, `calm`, `fluent`, `neutral` | Delivery style. Use auto to let the model choose, or pick a specific emotion |
| `english_normalization` | boolean | No | `false` |  | Improve number and date reading for English text (adds a small amount of latency) |
| `sample_rate` | integer | No | `32000` | `8000`, `16000`, `22050`, `24000`, `32000`, `44100` | Audio sample rate in Hz |
| `bitrate` | integer | No | `128000` | `32000`, `64000`, `128000`, `256000` | MP3 bitrate in bits per second. Only used when audio_format is mp3 |
| `audio_format` | string | No | `mp3` | `mp3`, `wav`, `flac`, `pcm` | File format of the generated audio: mp3 for general use, wav or flac for lossless, pcm for raw bytes |
| `channel` | string | No | `mono` | `mono`, `stereo` | mono for 1 channel (default), stereo for 2 channels |
| `subtitle_enable` | boolean | No | `false` |  | Request subtitle metadata with sentence timestamps (non-streaming only). The documented output of this API is the audio file URL |
| `language_boost` | string | No | `None` | `None`, `Automatic`, `Chinese`, `Chinese,Yue`, `Cantonese`, `English`, `Arabic`, `Russian`, `Spanish`, `French`, `Portuguese`, `German`, `Turkish`, `Dutch`, `Ukrainian`, `Vietnamese`, `Indonesian`, `Japanese`, `Italian`, `Korean`, `Thai`, `Polish`, `Romanian`, `Greek`, `Czech`, `Finnish`, `Hindi`, `Bulgarian`, `Danish`, `Hebrew`, `Malay`, `Persian`, `Slovak`, `Swedish`, `Croatian`, `Filipino`, `Hungarian`, `Norwegian`, `Slovenian`, `Catalan`, `Nynorsk`, `Tamil`, `Afrikaans` | Optional language hint. Choose Automatic to detect the language, or pick a specific language |

The full list of `language_boost` values is in the table above. `bitrate` only applies to `mp3` output.

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.013 per API unit.
- **1 API unit = 100 weighted tokens; an output token counts 0, an input token counts 1.** For this model 1 input token is 1 character of `text`, so 1 API unit = 100 characters.
- That works out to **$130 per million input tokens (characters)** and **$0 per million output tokens**; the length of the generated audio does not change the price.
- Each request is rounded up to a whole API unit, so every successful request costs at least $0.013.
- **Example cost**: the example text is 87 characters (87 input tokens), rounded up to 1 API unit = **$0.013**.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/high-fidelity-audio-generation-minimax-speech-2-8-hd`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/high-fidelity-audio-generation-minimax-speech-2-8-hd/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "minimax/speech-2.8-hd",
    "input": {
      "text": "Hello, world! This is a simple test of the MiniMax Speech 2.8 model, now on api.market.",
      "pitch": 0,
      "speed": 1,
      "volume": 1,
      "bitrate": 128000,
      "channel": "mono",
      "emotion": "auto",
      "voice_id": "Wise_Woman",
      "sample_rate": 32000,
      "audio_format": "mp3",
      "language_boost": "None",
      "subtitle_enable": false,
      "english_normalization": false
    }
  }'
```

Response (201 Created):
```json
{
  "id": "rk13j36va1rmy0d1c71s7kewx0",
  "version": "minimax/speech-2.8-hd",
  "status": "starting",
  "created_at": "2026-10-22T03:59:48.232Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/high-fidelity-audio-generation-minimax-speech-2-8-hd/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "rk13j36va1rmy0d1c71s7kewx0",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/speech-2-8-hd-output-rk13j36v-api-market.mp3",
  "error": null,
  "created_at": "2026-10-22T03:59:48.232Z",
  "started_at": "2026-10-22T03:59:49.232Z",
  "completed_at": "2026-10-22T03:59:51.196Z"
}
```

`output` is a single URL string pointing to the generated audio file.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `text`, a `speed` outside 0.5 to 2 or an `audio_format` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/high-fidelity-audio-generation-minimax-speech-2-8-hd";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "minimax/speech-2.8-hd", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "text": "Hello, world! This is a simple test of the MiniMax Speech 2.8 model, now on api.market.",
  "pitch": 0,
  "speed": 1,
  "volume": 1,
  "bitrate": 128000,
  "channel": "mono",
  "emotion": "auto",
  "voice_id": "Wise_Woman",
  "sample_rate": 32000,
  "audio_format": "mp3",
  "language_boost": "None",
  "subtitle_enable": false,
  "english_normalization": false
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/high-fidelity-audio-generation-minimax-speech-2-8-hd"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "minimax/speech-2.8-hd", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


output = create_and_wait_for_prediction({
    "text": "Hello, world! This is a simple test of the MiniMax Speech 2.8 model, now on api.market.",
    "pitch": 0,
    "speed": 1,
    "volume": 1,
    "bitrate": 128000,
    "channel": "mono",
    "emotion": "auto",
    "voice_id": "Wise_Woman",
    "sample_rate": 32000,
    "audio_format": "mp3",
    "language_boost": "None",
    "subtitle_enable": False,
    "english_normalization": False
})
print(output)
```

## FAQ
- **How is the price calculated?**
  - By the number of characters in `text`: $0.013 per 100 characters, rounded up per request. A 1,000-character text costs $0.13; the maximum of 10,000 characters costs $1.30.
- **Which voices can I use?**
  - Any MiniMax system voice ID, such as `English_Wiselady` (the default) or `English_Deep-VoicedGentleman`, or the `voice_id` of a voice you cloned with MiniMax.
- **How do I add a pause?**
  - Put a marker like `<#0.5#>` in `text`. The number is the pause length in seconds.
- **Which audio format should I pick?**
  - `mp3` for general use (set `bitrate` from 32000 to 256000), `wav` or `flac` for lossless audio, `pcm` for raw bytes.
- **Does subtitle_enable add timestamps to the output?**
  - The documented output is a single audio URL. Do not rely on subtitle data being returned.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Convert text to natural speech with MiniMax Speech 2.8 HD: system or cloned voices, emotion, speed, pitch and MP3, WAV, FLAC or PCM output.