# minimax/speech-2.6-hd

> Minimax Speech 2.6 HD: Ultra-human, low-latency (< 250ms) TTS with voice cloning, text normalization and support for 40+ languages. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

## Overview

- **Endpoint**: `https://api.wavespeed.ai/api/v3/minimax/speech-2.6-hd`
- **Polling/result URL**: `https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result`
- **Model ID**: `minimax/speech-2.6-hd`
- **Category**: text-to-speech

## Pricing

Billing is based on the length of your text: the price is proportional to the number of characters, at **$0.10 per 1,000 characters**. Voice, format, sample rate, and the other audio settings do not change the price.

| Text length | Price |
|---|---|
| 100 characters | $0.01 |
| 500 characters | $0.05 |
| 1,000 characters | $0.10 |
| 2,500 characters | $0.25 |
| 5,000 characters | $0.50 |
| 10,000 characters | $1.00 |

**Quick examples**

* 1,000 chars → **$0.10**
* 2,500 chars → **$0.25**
* 10,000 chars → **$1.00**

---

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
The API is asynchronous: submit a prediction, then poll its result URL until it completes.

### Input Schema

The API accepts the following input parameters:

- **`text`** (`string`, _required_):
  Text to convert to speech. Every character is 1 token. Maximum 10000 characters. Use <#x#> between words to control pause duration (0.01-99.99s).

- **`voice_id`** (`string`, _required_):
  Desired voice ID. Use a voice ID you have trained (https://wavespeed.ai/models/minimax/voice-clone), or one of the following system voice IDs: Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl.

- **`speed`** (`number`, _optional_):
  Speech speed. Range: 0.5-2.0, where 1.0 is normal speed.
  - Default: `1`
  - Range: `0.5` to `2`

- **`volume`** (`number`, _optional_):
  Speech volume. Range: 0.1-10.0, where 1.0 is normal volume.
  - Default: `1`
  - Range: `0.1` to `10`

- **`pitch`** (`number`, _optional_):
  Speech pitch. Range: -12 to 12, where 0 is normal pitch.
  - Default: `0`
  - Range: `-12` to `12`

- **`emotion`** (`string`, _optional_):
  The emotion of the generated speech.
  - Default: `"happy"`
  - Options: "happy", "sad", "angry", "fearful", "disgusted", "surprised", "neutral"

- **`english_normalization`** (`boolean`, _optional_):
  This parameter supports English text normalization, which improves performance in number-reading scenarios.
  - Default: `false`

- **`sample_rate`** (`integer`, _optional_):
  Sample rate of generated sound.
  - Options: 8000, 16000, 22050, 24000, 32000, 44100

- **`bitrate`** (`integer`, _optional_):
  Bitrate of generated sound.
  - Options: 32000, 64000, 128000, 256000

- **`channel`** (`string`, _optional_):
  The number of channels of the generated audio. 1: mono, 2: stereo.
  - Options: "1", "2"

- **`format`** (`string`, _optional_):
  Format of generated sound.
  - Options: "mp3", "wav", "pcm", "flac"

- **`language_boost`** (`string`, _optional_):
  Enhance the ability to recognize specified languages and dialects.
  - Options: "Chinese", "Chinese,Yue", "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", "auto"



**Required Parameters Example**:

```json
{
  "text": "A clear example input",
  "voice_id": "example"
}
```

**Full Example**:

```json
{
  "text": "A clear example input",
  "voice_id": "example",
  "speed": 1,
  "volume": 1,
  "pitch": 0,
  "emotion": "happy",
  "english_normalization": false,
  "sample_rate": 8000,
  "bitrate": 32000,
  "channel": "1",
  "format": "mp3",
  "language_boost": "Chinese"
}
```

### Result Data Schema

The `data` object returned by the API has the following fields:

- **`created_at`** (`string (date-time)`, _optional_):
  ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

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

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

- **`outputs`** (`array of string | object`, _optional_):
  Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.

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

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



**Example `data` Object**:

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

## Usage Examples

The examples use `jq` to read JSON. Set your API key first:

```bash
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
```

### 1. Submit a prediction

```bash
REQUEST_BODY=$(cat <<'JSON'
{
  "text": "A clear example input",
  "voice_id": "example"
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url https://api.wavespeed.ai/api/v3/minimax/speech-2.6-hd \
  --header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  --header "Content-Type: application/json" \
  --data "${REQUEST_BODY}")

printf '%s\n' "${SUBMIT_RESPONSE}" | jq .
```

The response contains the prediction ID in `data.id`.

### 2. Poll until complete and read `outputs`

```bash
PREDICTION_ID=$(printf '%s' "${SUBMIT_RESPONSE}" | jq -r '.data.id')
if [ -z "${PREDICTION_ID}" ] || [ "${PREDICTION_ID}" = "null" ]; then
  printf 'Submission response did not contain data.id\n' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    --request GET \
    --url "${RESULT_URL}" \
    --header "Authorization: Bearer ${WAVESPEED_API_KEY}")

  RESULT=$(printf '%s' "${RESPONSE}" | jq -e '.data')
  STATUS=$(printf '%s' "${RESULT}" | jq -er '.status')
  case "${STATUS}" in
    completed)
      # Generated files are returned in the outputs array.
      printf '%s\n' "${RESULT}" | jq '.outputs'
      break
      ;;
    failed|cancelled|timeout|deleted)
      printf '%s\n' "${RESULT}" | jq '{status, error, code}'
      exit 1
      ;;
    *)
      sleep 2
      ;;
  esac
done
```

## Additional Resources

### Documentation

- [Model Playground](https://wavespeed.ai/models/minimax/speech-2.6-hd)
- [API Documentation](https://wavespeed.ai/docs/docs-api/minimax/minimax-speech-2.6-hd)
