# Kling Custom Voice — Atlas Cloud API

> Clone a reusable voice from a 5-30 second speech sample (or from a previously generated video) and get a voice_id the Kling 4.0 reference-to-video and video-edit models accept, plus an audition clip.

This is the machine-readable API reference for **Kling Custom Voice** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `kwaivgi/kling-v4.0/custom-voice`
- **Built by**: Kuaishou
- **Modality**: Audio
- **Model page**: https://www.atlascloud.ai/models/kwaivgi/kling-v4.0/custom-voice
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.006 per 1K characters
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_audio` with `model: "kwaivgi/kling-v4.0/custom-voice"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas models get kwaivgi/kling-v4.0/custom-voice --json
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateAudio` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `kwaivgi/kling-v4.0/custom-voice`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"kwaivgi/kling-v4.0/custom-voice"`

- **`voice_name`** (`string`, _required_):
  Name for the new voice. At most 20 characters.
  - Default: `"My Voice"`

- **`audio`** (`string`, _optional_):
  Speech sample to clone, as a URL. 5-30 seconds of a single clean voice, mp3/wav/mp4/mov, up to 50MB. Mutually exclusive with video_id.

- **`video_id`** (`string`, _optional_):
  Clone the voice from a previously generated video instead of an uploaded sample. The video must come from Kling V2.6 with sound enabled, the Avatar API, or the Lip-Sync API. Mutually exclusive with audio.



**Required Parameters Example**:

```json
{
  "model": "kwaivgi/kling-v4.0/custom-voice",
  "voice_name": "My Voice",
  "audio": "https://example.com/sample.mp3"
}
```


**Full Example**:

```json
{
  "model": "kwaivgi/kling-v4.0/custom-voice",
  "voice_name": "My Voice",
  "audio": "https://example.com/sample.mp3"
}
```


### Output Schema

The API returns the following output format:


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

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

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

- **`outputs`** (`array[string]`, _optional_):
  Array holding the audition clip for the created voice.

- **`voice_result`** (`object`, _optional_):
  The created voice.
  - Properties:
    - **`voice_id`** (`string`, _optional_):
      The voice identifier, always a string (an 18-digit number). Pass it verbatim in the voice_ids field of the reference-to-video / video-edit models.

    - **`voice_name`** (`string`, _optional_):
      The name given at creation time.

    - **`trial_url`** (`string`, _optional_):
      Audition clip for the voice.

    - **`owned_by`** (`string`, _optional_):
      "kling" for a voice from the official preset library, the creator's ID for a custom voice.


- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

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



**Example Response**:

```json
{
  "code": 200,
  "data": {
    "id": "prediction_id",
    "status": "completed",
    "voice_result": {
      "voice_id": "850087542757535834",
      "voice_name": "My Voice",
      "trial_url": "https://example.com/audition.mp3",
      "owned_by": "your-account"
    }
  }
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateAudio" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kwaivgi/kling-v4.0/custom-voice",
  "voice_name": "My Voice",
  "audio": "https://example.com/sample.mp3"
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, read data.voice_result.voice_id as a string and data.voice_result.trial_url for the audition URL. Use audio OR video_id, never both.
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/kwaivgi/kling-v4.0/custom-voice)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Kling Custom Voice

**Kling Custom Voice** clones a reusable voice from a short speech sample. It returns a `voice_id` that the Kling 4.0 Reference-to-Video and Video-Edit models accept in their `voice_ids` field, plus an audition clip so you can hear the result before using it.

#### Why Choose This?

- **Create once, reuse forever.** One `voice_id` drives speech across every later generation.
- **Two sources.** Clone from an uploaded speech sample, or from a video you already generated.
- **Audition included.** Every created voice comes with a trial clip.

#### Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| model | Yes | `kwaivgi/kling-v4.0/custom-voice` |
| voice_name | Yes | Name for the new voice. At most 20 characters. |
| audio | One of the two | Speech sample URL: 5–30 seconds of a single clean voice, MP3 / WAV / MP4 / MOV, up to 50MB. |
| video_id | One of the two | A previously generated video to clone the voice from, instead of an uploaded sample. |

`audio` and `video_id` are mutually exclusive — provide exactly one. A `video_id` must come from Kling V2.6 with sound enabled, the Avatar API, or the Lip-Sync API.

#### How to Use

```bash
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateAudio" \
  -H "Authorization: Bearer $AIP_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "kwaivgi/kling-v4.0/custom-voice",
    "voice_name": "Narrator",
    "audio": "https://example.com/sample.mp3"
  }'
```

Creation is asynchronous. The response contains a request `id`; poll `GET https://api.atlascloud.ai/api/v1/model/prediction/{id}` until `status` is `completed`, then read the voice from `voice_result`:

```json
{
  "status": "completed",
  "outputs": ["https://.../trial.mp3"],
  "voice_result": {
    "voice_id": "850087542757535834",
    "voice_name": "Narrator",
    "trial_url": "https://.../trial.mp3",
    "owned_by": "..."
  }
}
```

Then pass the voice to a video generation:

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/kwaivgi/kling-v4.0/custom-voice · Docs: https://www.atlascloud.ai/docs
