# Train Rvc

Realistic Voice Cloning v2 (RVC v2) is an advanced voice-to-voice model that transforms an input voice into a chosen target voice with realistic results, accessible through the RVC v2 Web UI on Replicate.

## API Information

- **Model Slug:** train-rvc
- **Branded URL:** https://www.eachlabs.ai/eachlabs/eachlabs/train-rvc
- **Provider:** each::labs
- **Category:** Training
- **Output Type:** text
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier.
- **Estimated Processing Time:** 80 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/train-rvc

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| dataset_zip | string | Yes | - | - | Upload dataset zip, zip should contain `dataset/<rvc_name>/split_<i>.wav` |
| sample_rate | string | No | 48k | 40k,48k | An enumeration. |
| version | string | No | v2 | v1,v2 | An enumeration. |
| f0method | string | No | rmvpe_gpu | pm,dio,harvest,rmvpe,rmvpe_gpu | An enumeration. |
| epoch | integer | No | 10 | - | Epoch |
| batch_size | string | No | 7 | - | Batch size |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "train-rvc",
  "input": {
    "dataset_zip": "https://storage.googleapis.com/magicpoint/inputs/dataset.zip"
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "text",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer 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 `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**train-rvc — Voice Cloning AI Model**

train-rvc is an advanced voice cloning model that transforms any input voice into a target voice with remarkable realism and naturalness. Developed by Eachlabs as part of the eachlabs family, train-rvc solves a critical problem for content creators, developers, and media professionals: the ability to clone voices quickly and affordably without expensive studio sessions or complex training pipelines. Whether you're building an AI voice generator for podcasts, creating multilingual content, or developing applications that require realistic voice synthesis, train-rvc delivers production-ready voice conversion in seconds.

The model's primary strength lies in its ability to perform zero-shot voice cloning—meaning it can clone voices from minimal audio samples without requiring extensive preprocessing or model retraining. This makes train-rvc uniquely accessible for rapid prototyping and real-world deployment, setting it apart from voice cloning solutions that demand large datasets or lengthy training periods.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer 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.