# Eleven v4

> Most expressive voice engine — audio tags direct the delivery, 90+ languages.

## Overview

- **Model ID**: `eleven-v4`
- **Workflow**: `elevenlabs/v1/text-to-speech`
- **Provider**: ElevenLabs
- **Category**: Text → Speech (audio)
- **Output**: An audio URL.
- **Tags**: new, popular, audio tags, 90+ languages, creative control
- **Unified endpoint**: `POST https://api.picsart.com/workflows/v1/models/execute` (model id in the body)
- **Compatibility endpoint**: `POST https://api.picsart.com/workflows/elevenlabs/v1/text-to-speech/execute` (vendor's own parameters)
- **Execution**: long-running — use the async submit/poll pair or the SDK, which polls for you
- **Model page**: https://picsart.com/api-platform/models/eleven-v4

## Pricing

Rates are in USD. Every row below is an exact rate for the settings it names — the columns are the settings that change the price for this model. Every response reports what was actually charged in `response.usage.credits`.

| Rate |
| --- |
| $0.290909 / 1K chars |

Published rates. Volume pricing, invoicing and annual agreements: https://picsart.com/api-platform/contact-sales

## Authentication

The SDK and the REST API authenticate with a Picsart API key sent as a bearer token. Create a key in the console at https://picsart.com/api-platform/dashboard/api-keys, keep it in a server-side environment variable, and never ship it in browser code or commit it.

```bash
export PICSART_API_KEY="YOUR_KEY"
```

```http
Authorization: Bearer $PICSART_API_KEY
```

The CLI and the MCP server do not use an API key: `gen-ai login` signs in through the browser once per machine and stores a token locally.

## Interfaces

- **SDK** — `@picsart/ai-sdk` (TypeScript, Node 20+, ESM). Type-safe `ai.generate()` / `ai.generateText()` with per-model parameter types; polls long jobs for you.
- **REST** — the API gateway at `https://api.picsart.com`. Sync `/execute`, or async `/submit` + `/{taskId}/result`.
- **CLI** — `@picsart/gen-ai` (`gen-ai`). Generate from a terminal, quote cost before spending, emit JSON for pipelines.
- **MCP** — the same models inside Claude Code, Cursor, Windsurf and other MCP hosts. Setup: https://picsart.com/gen-ai-mcp/

```bash
npm install @picsart/ai-sdk      # SDK
npm install -g @picsart/gen-ai   # CLI (also drives the MCP server)
```

## Unified API (recommended)

One parameter set, used by the SDK and by REST alike: the names below are what `ai.generate('eleven-v4', …)` takes, and what goes inside the inner `params` of a REST call. Over REST the model id travels in the body, not the path — one workflow, `v1/models`, fronts the whole catalogue.

### Execution modes

- **Sync** — `POST /workflows/v1/models/execute` returns the result in one call. Only for jobs that finish within ~20 seconds; otherwise it times out.
- **Async** — `POST /workflows/v1/models/submit` returns a task id; poll `GET /workflows/v1/models/{taskId}/result` until `response.status` is `COMPLETED` or `FAILED`. Task statuses: `ACCEPTED` · `IN_PROGRESS` · `COMPLETED` · `FAILED`.
- **SDK** — `ai.generate()` always awaits the finished result; polling is hidden.

Audio jobs routinely outrun the sync limit: use async over REST, or the SDK, which polls for you.

### Input parameters

- **`language`** (`string`, _optional_): Language
- **`prompt`** (`string`, _required_): Prompt
  - Max length: 10000 characters
- **`voiceId`** (`string`, _optional_): Voice
  - An id from the `elevenlabs/v1/catalog/voices` catalog, fetched at runtime via `ai.catalogs`
  - Default: `JBFqnCBsd6RMkjVDRZzb`
- **`stability`** (`number`, _optional_): Stability
  - Range: 0–1 (step 0.05)
- **`similarityBoost`** (`number`, _optional_): Similarity
  - Range: 0–1 (step 0.05)
- **`withTimestamps`** (`boolean`, _optional_): Character Timings
  - Default: `false`

### Input JSON Schema

The inner `params` object. Over REST it is wrapped as `{ "params": { "model": "<id>", "params": <this> } }`; the SDK takes it directly.

```json
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "language": {
      "type": "string",
      "description": "Language"
    },
    "prompt": {
      "type": "string",
      "maxLength": 10000,
      "description": "Prompt"
    },
    "voiceId": {
      "type": "string",
      "description": "Voice — an id from the `elevenlabs/v1/catalog/voices` catalog",
      "default": "JBFqnCBsd6RMkjVDRZzb"
    },
    "stability": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "multipleOf": 0.05,
      "description": "Stability"
    },
    "similarityBoost": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "multipleOf": 0.05,
      "description": "Similarity"
    },
    "withTimestamps": {
      "type": "boolean",
      "default": false,
      "description": "Character Timings"
    }
  },
  "additionalProperties": false
}
```

### Required parameters example

The required parameters plus the defaults that shape the output, as a REST body:

```json
{
  "params": {
    "model": "eleven-v4",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed"
    }
  }
}
```

### Response

The body is the gateway's status envelope: the output is at `response.result`, next to the task id, its status and the credits charged. Asset models return `url` plus an `items` array of results.

```json
{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result",
      "items": [
        {
          "url": "https://cdn.picsart.com/…/result"
        }
      ],
      "model": "eleven-v4"
    }
  }
}
```

What `ai.generate()` / `ai.generateText()` resolve to (the envelope already unwrapped):

```json
{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "eleven-v4"
}
```

### Usage examples

#### TypeScript (SDK)

```typescript
import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const result = await ai.generate('eleven-v4', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
});

console.log(result.url); // audio URL
```

#### cURL (sync)

```bash
curl -X POST 'https://api.picsart.com/workflows/v1/models/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "eleven-v4",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed"
    }
  }
}'
```

#### cURL (async: submit, then poll)

```bash
# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/v1/models/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "eleven-v4",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed"
    }
  }
}'
# → { "status": "success", "response": { "id": "task_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/v1/models/task_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'
```

#### CLI

```bash
gen-ai login  # once per machine
gen-ai models info eleven-v4  # this model's parameters
gen-ai pricing eleven-v4  # quote before spending credits
gen-ai generate -m eleven-v4 \
  -p "A serene mountain lake at golden hour"
```

## Compatibility API (vendor parameters)

Alongside the unified API, the `elevenlabs/v1/text-to-speech` workflow takes ElevenLabs's own parameters exactly as the vendor defines them — nothing renamed or reshaped. It is the shortest path onto Picsart for request bodies already written against the vendor; the trade is that a request is written for one vendor, and the result comes back in the vendor's own shape. Same authentication.

- **Endpoint**: `POST https://api.picsart.com/workflows/elevenlabs/v1/text-to-speech/execute` (sync) · `POST …/submit` + `GET …/{taskId}/result` (async)
- **SDK**: `ai.apis.run('elevenlabs/v1/text-to-speech', params, { mode })` — params forwarded verbatim

### Vendor parameters

| Parameter | Type | Required | Default | Details |
| --- | --- | --- | --- | --- |
| `voice_id` | `string` | yes | — | ID of the ElevenLabs voice to use · e.g. `21m00Tcm4TlvDq8ikWAM` |
| `text` | `string` | yes | — | The text to convert to speech. On eleven_v3, eleven_v4 and eleven_v4_turbo, bracketed audio tags such as [whispering] or [laughing] direct the delivery. Per-request cap: 10,000 characters (5,000 on eleven_v3). · e.g. `Hello, welcome to our product demo.` |
| `model_id` | `string` | no | `eleven_multilingual_v2` | The model to use for text-to-speech. eleven_v4 is the most expressive engine (90+ languages, 10,000 characters); eleven_v4_turbo trades some quality for latency. With a language_code that differs from the voice, v4 speaks the target language natively instead of carrying the voice's accent. · Options: `eleven_multilingual_v2`, `eleven_v3`, `eleven_v4`, `eleven_v4_turbo` |
| `output_format` | `string` | no | `mp3_44100_128` | Output audio format · Options: `mp3_22050_32`, `mp3_44100_32`, `mp3_44100_64`, `mp3_44100_96`, `mp3_44100_128`, `mp3_44100_192`, `mp3_48000_192`, `pcm_16000`, `pcm_22050`, `pcm_24000`, `pcm_44100`, `pcm_48000` |
| `voice_settings` | `object` | no | — | Voice settings to override stored defaults |
| └ `stability` | `number` | no | — | Voice consistency (0-1). Lower = more variation. |
| └ `similarity_boost` | `number` | no | — | Adherence to original voice (0-1) |
| └ `style` | `number` | no | — | Style exaggeration intensity (0-1). Ignored by eleven_v4 and eleven_v4_turbo, which take delivery direction from audio tags in the text instead. |
| └ `speed` | `number` | no | `1` | Speech rate multiplier. Ignored by eleven_v4 and eleven_v4_turbo. |
| └ `use_speaker_boost` | `boolean` | no | `true` | Boost similarity to the original speaker. Ignored by eleven_v4 and eleven_v4_turbo. |
| `language_code` | `string` | no | — | ISO 639-1 language code for text normalization · e.g. `en` |
| `with_timestamps` | `boolean` | no | `false` | Return per-character timings alongside the audio, for captions and lip sync |
| `seed` | `number` | no | — | Seed for deterministic generation (0-4294967295) |
| `options` | `object` | no | — | Options controlling safety checks and drive integration |
| └ `safety_checks` | `object` | no | — | Safety check settings |
| └   `enabled` | `boolean` | no | — | Whether to run content moderation. Defaults to true. |
| └ `drive` | `object` | no | — | Save result to Picsart Drive |
| └   `name` | `string` | yes | — | File name in Picsart Drive |
| └   `attributes` | `object` | no | — | Custom attributes to attach to the file |
| └   `folder` | `object` | no | — | Target folder in Picsart Drive |
| └ `inputs_transformation` | `object` | no | — | Input transformation settings |
| └   `downscale_oversized_images` | `boolean` | no | — | Whether to downscale oversized input images. Defaults to false. |

### Example request body

```json
{
  "params": {
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "text": "Hello, welcome to our product demo."
  }
}
```

### Usage examples

#### TypeScript (`ai.apis.run`)

```typescript
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Calls the 'elevenlabs/v1/text-to-speech' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('elevenlabs/v1/text-to-speech', {
  voice_id: "21m00Tcm4TlvDq8ikWAM",
  text: "Hello, welcome to our product demo."
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // amount charged, in $
```

#### cURL (sync)

```bash
curl -X POST 'https://api.picsart.com/workflows/elevenlabs/v1/text-to-speech/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "text": "Hello, welcome to our product demo."
  }
}'
```

#### cURL (async: submit, then poll)

```bash
# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/elevenlabs/v1/text-to-speech/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "text": "Hello, welcome to our product demo."
  }
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/elevenlabs/v1/text-to-speech/wf_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'
```

### Response

Over HTTP the vendor-shaped result arrives inside the gateway envelope at `response.result`:

```json
{
  "status": "success",
  "response": {
    "id": "wf_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result.mp3",
      "mimeType": "audio/mpeg",
      "driveFile": {},
      "alignment": {
        "characters": [
          "…"
        ],
        "character_start_times_seconds": [
          0
        ],
        "character_end_times_seconds": [
          0
        ]
      },
      "normalizedAlignment": {
        "characters": [
          "…"
        ],
        "character_start_times_seconds": [
          0
        ],
        "character_end_times_seconds": [
          0
        ]
      }
    }
  }
}
```

`ai.apis.run()` unwraps that envelope and resolves to `{ result, usage }`:

```json
{
  "result": {
    "url": "https://cdn.picsart.com/…/result.mp3",
    "mimeType": "audio/mpeg",
    "driveFile": {},
    "alignment": {
      "characters": [
        "…"
      ],
      "character_start_times_seconds": [
        0
      ],
      "character_end_times_seconds": [
        0
      ]
    },
    "normalizedAlignment": {
      "characters": [
        "…"
      ],
      "character_start_times_seconds": [
        0
      ],
      "character_end_times_seconds": [
        0
      ]
    }
  }
}
```

## Additional resources

- Model page: https://picsart.com/api-platform/models/eleven-v4
- Try it: https://picsart.com/api-platform/models/eleven-v4/playground
- SDK: https://picsart.com/api-platform/models/eleven-v4/sdk
- REST API (unified): https://picsart.com/api-platform/models/eleven-v4/api
- Compatibility API (vendor parameters): https://picsart.com/api-platform/models/eleven-v4/advanced
- Pricing: https://picsart.com/api-platform/models/eleven-v4/pricing
- This document: https://picsart.com/api-platform/models/eleven-v4/llms.txt
- All models: https://picsart.com/api-platform/models
- Docs — quickstart https://picsart.com/api-platform/docs/quickstart, authentication https://picsart.com/api-platform/docs/authentication, SDK https://picsart.com/api-platform/docs/sdk, REST https://picsart.com/api-platform/docs/api-reference, CLI https://picsart.com/api-platform/docs/cli, MCP https://picsart.com/api-platform/docs/mcp
- CLI reference: https://picsart.github.io/picsart-mcp-cli-docs/guide/introduction