# Mureka | Create Speech

Mureka Create Speech is a text-to-speech model that converts written input into natural-sounding spoken audio.

## API Information

- **Model Slug:** mureka-create-speech
- **Branded URL:** https://www.eachlabs.ai/mureka/mureka/mureka-create-speech
- **Provider:** Mureka
- **Category:** Music Generation
- **Output Type:** object
- **Status:** active
- **Version:** 0.0.1
- **Estimated Processing Time:** 10 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/mureka-create-speech

## Pricing

Pricing information not available.

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| voice_id | string | No | - | - | Control audio generation by referencing voice, generated through the files/upload API (for voice purpose). When this option is selected, other control options (voice) cannot be selected. |
| voice | string | No | - | Ethan,Victoria,Jake,Luna,Emma,Null | The voice to use when generating the audio. When this option is selected, other control options (voice_id) cannot be selected. |
| text | string | Yes | - | - | - |

## 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": "mureka-create-speech",
  "input": {
    "text": "Today is about progress, not perfection. Every small step we take, every idea we try, brings us closer to something better. What matters most is staying curious, staying brave, and continuing to build, even when the path isn’t clear yet."
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "object",
  "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

**mureka-create-speech — Music Generation AI Model**

Developed by Mureka as part of the mureka family, **mureka-create-speech** is a specialized text-to-speech model that transforms written text into natural-sounding spoken audio with expressive vocal synthesis, ideal for music production and content creation. This music-generation AI model stands out by integrating high-quality speech synthesis directly into musical compositions, enabling seamless vocal tracks from simple prompts. Users searching for "Mureka music-generation" or "text-to-speech for music AI" find **mureka-create-speech** excels in generating realistic vocals across 10+ languages, perfect for creators needing professional audio without recording studios.

## 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.