> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vmeg.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Supported clone methods

> Voice provider codes and clone engines V1–V5

Open API uses short **provider codes** in voice lists, translation results, and clone requests — **`S1`–`S7`** for system presets and **`V1`–`V5`** for clones.

## Provider codes at a glance

| Code pattern  | Used for                     | Where you see it                                                                                      |
| ------------- | ---------------------------- | ----------------------------------------------------------------------------------------------------- |
| **`S1`–`S7`** | System preset voices         | [List system voices](/api-reference/assets/voices/list-system-voices), media translation line results |
| **`V1`–`V5`** | Cloned voices and clone jobs | [Voice clone](/guides/products/voice-clone), clone list, media translation when cloning is enabled    |

System preset tiers are **`S1` through `S7`**, including Cantonese presets on **`S7`**.

Copy **`voiceId` and `provider` together** from API responses when you need to resubmit or edit content (especially media translation lines). See [Voices](/guides/assets/voices).

## Where you send `provider`

| Product                                                 | Field                                                                                                                                         |
| ------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
| [Text to speech](/guides/products/text-to-speech)       | **Do not send** — use `voiceId` only                                                                                                          |
| [Voice clone](/guides/products/voice-clone)             | `provider` (`V1`–`V5`) when creating a clone                                                                                                  |
| [Media translation](/guides/products/media-translation) | `options.voiceClone.provider` (`V1`–`V5`) when voice cloning is enabled; optional on `selectedVoicesList` if you already know the preset tier |

## Clone engines (`V1`–`V5`)

Pass **`V1` through `V5`** when creating a cloned voice or when media translation uses voice cloning. These match the clone options on [vmeg.ai](https://www.vmeg.ai/home).

| `provider` | Best for                                                               |
| ---------- | ---------------------------------------------------------------------- |
| `V1`       | Simple cloning — short sentences, everyday dialogue                    |
| `V2`       | Films, dramas, storytelling — emotional shifts and tone detail         |
| `V3`       | General use with more accurate, natural cloning for **English** voices |
| `V4`       | Authentic emotion and subtle mood changes; strongest nuance            |
| `V5`       | **Non-English** and multilingual voices                                |

### Choosing a clone engine

| Your content                       | Suggested `provider` |
| ---------------------------------- | -------------------- |
| Short lines, light usage           | `V1`                 |
| Drama, film, strong performance    | `V2` or `V4`         |
| Mostly English source/target       | `V3`                 |
| Mostly non-English or multilingual | `V5`                 |

## Text to speech: `voiceId` and batch rules

[Text to speech](/guides/products/text-to-speech) accepts up to 50 lines in `data[]` per request.

**Use `voiceId` from [Voices](/guides/assets/voices).** Do not send `provider` on TTS requests.

Batch rules:

**Every `voiceId` must exist.** If an ID is not in your system or clone library, the API returns `400` and points you to `POST /openapi/v1/assets/voice/basic/list` or `POST /openapi/v1/assets/voice/clone/list`.

**All lines in one request must use compatible voices** — same preset tier (`S*`) for system voices, or the same clone engine (`V1`–`V5`) for clones. For example, you cannot mix `S1` and `S2` presets, or `V1` and `V2` clones, in one request.

**`timbreRefAudio` is clone-only.** If any line uses `timbreRefAudio`, every voice in that batch must be a clone engine (`V1`–`V5`). Do not mix `timbreRefAudio` with system preset `voiceId`s in the same batch.

See [Error codes](/guides/errors) → **TTS voice validation** for example messages.

<Note>
  Language locale codes are listed in [Supported languages](/guides/supported-languages). `provider` selects the **engine family**, not the language.
</Note>