# Minimax | Speech | 2.8 | Turbo

MiniMax Speech 2.8 Turbo creates fast, low-latency AI voice output from text for real-time agents, IVR, and high-volume narration on eachlabs.

## API Information

- **Model Slug:** minimax-speech-2-8-turbo
- **Branded URL:** https://www.eachlabs.ai/minimax/minimax-speech/minimax-speech-2-8-turbo
- **Provider:** Minimax
- **Category:** Text to Voice
- **Output Type:** audio
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** MiniMax Speech 2.8 Turbo: $0.06 per 1,000 characters of input prompt.
- **Estimated Processing Time:** 6 seconds
- **Last Updated:** 2026-05-08
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-speech-2-8-turbo

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0166
- **Pricing Details:** MiniMax Speech 2.8 Turbo: $0.06 per 1,000 characters of input prompt.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | MiniMax Speech 2.8 Turbo: $0.06 per 1,000 characters of input prompt. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text to convert to speech. Use `<#x#>` for pauses (x = 0.01-99.99 seconds). Supports interjection tags: `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, `(yawns)`. |
| voice_setting | string | No | {'vol': 1, 'speed': 1, 'voice_id': 'Wise_Woman', 'pitch': 0, 'english_normalization': False} | - | Voice configuration settings |
| audio_setting | string | No | - | - | Audio configuration settings |
| language_boost | string | No | - | - | Enhance recognition of specified languages and dialects |
| output_format | string | No | hex | url, hex | Format of the output content (non-streaming only) |
| pronunciation_dict | string | No | - | - | Custom pronunciation dictionary for text replacement |
| normalization_setting | string | No | - | - | Loudness normalization settings for the audio |
| voice_modify | string | No | - | - | Voice modification settings to adjust pitch, intensity, and timbre. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-speech-2-8-turbo",
  "input": {
    "prompt": "A rabbit and a tortoise decided to race. The rabbit, confident in his speed, sprinted ahead — then stopped to rest under a tree. The tortoise never paused, never doubted, just kept moving. By the time the rabbit opened his eyes, the tortoise had already crossed the finish line"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated audio)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Minimax | Speech | 2.8 | Turbo Overview**

Minimax | Speech | 2.8 | Turbo is a high-speed text-to-voice model from the Minimax provider, part of the minimax-speech family, designed for generating natural-sounding AI voice output from text inputs. It excels in delivering low-latency speech synthesis, making it ideal for real-time applications where speed is critical. Unlike standard text-to-speech models, this Turbo variant prioritizes ultra-fast inference while maintaining high voice quality, enabling seamless integration into live agents, interactive voice response (IVR) systems, and high-volume narration workflows on each::labs.

Available via the **Minimax | Speech | 2.8 | Turbo API** on eachlabs.ai, it transforms simple text prompts into expressive audio clips. Developers and creators leverage its efficiency for dynamic content generation, reducing wait times to milliseconds. This model addresses key challenges in voice AI by balancing performance and realism, positioning it as a go-to for scalable, responsive audio production.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.