# Gemini 3.8 Flash TTS

> Latest Gemini native text-to-speech with directable delivery and inline vocal events like <laugh> and <sigh>.

## Overview

- **Model ID**: `gemini-3.8-flash-tts`
- **Workflow**: `gemini/v1/audios`
- **Provider**: Google
- **Category**: Text → Speech (audio)
- **Output**: An audio URL.
- **Tags**: multilingual, 30 voices, multi-speaker, style direction
- **Unified endpoint**: `POST https://api.picsart.com/workflows/v1/models/execute` (model id in the body)
- **Compatibility endpoint**: `POST https://api.picsart.com/workflows/gemini/v1/audios/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/gemini-3.8-flash-tts

## 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 |
| --- |
| $18.00 / 1M output text tokens |

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('gemini-3.8-flash-tts', …)` 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
- **`accent`** (`string`, _optional_): Accent
- **`prompt`** (`string`, _optional_): Prompt
  - Max length: 6000 characters
- **`voiceId`** (`string`, _optional_): Voice
  - An id from the `gemini/v1/catalog/voices` catalog, fetched at runtime via `ai.catalogs`
  - Default: `Kore`
- **`style`** (`string`, _optional_): Style
  - Max length: 500 characters
  - e.g. "e.g. warm, unhurried; a bedtime story"
- **`parts`** (`object`, _optional_): Spoken Parts
  - Fields: `text`, `speaker`, `style`
- **`multiSpeakerVoiceConfigs`** (`object`, _optional_): Speakers
  - Fields: `speaker`, `voiceName`

### 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",
  "properties": {
    "language": {
      "type": "string",
      "description": "Language"
    },
    "accent": {
      "type": "string",
      "description": "Accent"
    },
    "prompt": {
      "type": "string",
      "maxLength": 6000,
      "description": "Prompt"
    },
    "voiceId": {
      "type": "string",
      "description": "Voice — an id from the `gemini/v1/catalog/voices` catalog",
      "default": "Kore"
    },
    "style": {
      "type": "string",
      "maxLength": 500,
      "description": "Style"
    },
    "parts": {
      "type": "object",
      "properties": {
        "text": {},
        "speaker": {},
        "style": {}
      },
      "description": "Spoken Parts"
    },
    "multiSpeakerVoiceConfigs": {
      "type": "object",
      "properties": {
        "speaker": {},
        "voiceName": {}
      },
      "description": "Speakers"
    }
  },
  "additionalProperties": false
}
```

### Required parameters example

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

```json
{
  "params": {
    "model": "gemini-3.8-flash-tts",
    "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": "gemini-3.8-flash-tts"
    }
  }
}
```

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

```json
{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "gemini-3.8-flash-tts"
}
```

### 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('gemini-3.8-flash-tts', {
  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": "gemini-3.8-flash-tts",
    "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": "gemini-3.8-flash-tts",
    "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 gemini-3.8-flash-tts  # this model's parameters
gen-ai pricing gemini-3.8-flash-tts  # quote before spending credits
gen-ai generate -m gemini-3.8-flash-tts \
  -p "A serene mountain lake at golden hour"
```

## Compatibility API (vendor parameters)

Alongside the unified API, the `gemini/v1/audios` workflow takes Google'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/gemini/v1/audios/execute` (sync) · `POST …/submit` + `GET …/{taskId}/result` (async)
- **SDK**: `ai.apis.run('gemini/v1/audios', params, { mode })` — params forwarded verbatim

### Vendor parameters

| Parameter | Type | Required | Default | Details |
| --- | --- | --- | --- | --- |
| `text` | `string` | no | — | Text to synthesize into speech (single part). Ignored when `parts` is given. |
| `style` | `string` | no | — | Delivery direction for the whole text; shorthand for a single part's `style`. Honoured by the 3.8 models. |
| `parts` | `SpeechPartDto[]` | no | — | Ordered spoken parts with optional per-part speaker and style. Use instead of `text` for directed or multi-speaker speech. · max 200 items |
| └ `text` | `string` | yes | — | Verbatim text to speak. On 3.8, angle-bracket vocal events (<laugh>, <sigh>, <breath>, <short pause>) are honoured inline. |
| └ `speaker` | `string` | no | — | Speaker name; must match a `multiSpeakerVoiceConfigs` entry. Required on every part of a multi-speaker request. |
| └ `style` | `string` | no | — | Natural-language delivery direction for this part, e.g. "frightened, breathy whisper; a scared little girl". Sent as speechMetadata.style, never spoken. |
| `model` | `string` | yes | — | TTS model to use · Options: `gemini-2.5-flash-tts`, `gemini-2.5-pro-tts`, `gemini-3.8-flash-tts`, `gemini-3.8-flash-lite-tts` |
| `voiceName` | `string` | no | — | Voice name for single-speaker TTS · Options: `Puck`, `Kore`, `Charon`, `Fenrir`, `Aoede`, `Leda`, `Zephyr`, `Orus`, `Autonoe`, `Callirrhoe`, `Despina`, `Erinome`, `Gacrux`, `Laomedeia`, `Pulcherrima`, `Sulafat`, `Vindemiatrix`, `Achernar`, `Achird`, `Algenib`, `Algieba`, `Alnilam`, `Enceladus`, `Iapetus`, `Rasalgethi`, `Sadachbia`, `Sadaltager`, `Schedar`, `Umbriel`, `Zubenelgenubi` |
| `multiSpeakerVoiceConfigs` | `SpeakerVoiceConfigDto[]` | no | — | Multi-speaker voice configs (max 2). When provided, voiceName is ignored. · max 2 items |
| └ `speaker` | `string` | yes | — | Speaker identifier (e.g. "Speaker 1") |
| └ `voiceName` | `string` | yes | — | Voice name for this speaker · Options: `Puck`, `Kore`, `Charon`, `Fenrir`, `Aoede`, `Leda`, `Zephyr`, `Orus`, `Autonoe`, `Callirrhoe`, `Despina`, `Erinome`, `Gacrux`, `Laomedeia`, `Pulcherrima`, `Sulafat`, `Vindemiatrix`, `Achernar`, `Achird`, `Algenib`, `Algieba`, `Alnilam`, `Enceladus`, `Iapetus`, `Rasalgethi`, `Sadachbia`, `Sadaltager`, `Schedar`, `Umbriel`, `Zubenelgenubi` |
| `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": {
    "text": "Hello, welcome to our product demo.",
    "model": "gemini-2.5-flash-tts"
  }
}
```

### 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 'gemini/v1/audios' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('gemini/v1/audios', {
  text: "Hello, welcome to our product demo.",
  model: "gemini-2.5-flash-tts"
}, {
  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/gemini/v1/audios/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "text": "Hello, welcome to our product demo.",
    "model": "gemini-2.5-flash-tts"
  }
}'
```

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

```bash
# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/gemini/v1/audios/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "text": "Hello, welcome to our product demo.",
    "model": "gemini-2.5-flash-tts"
  }
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/gemini/v1/audios/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": {
      "audioUrls": [
        {
          "url": "https://cdn.picsart.com/…/result.mp3",
          "mimeType": "audio/mpeg",
          "driveFile": {}
        }
      ]
    }
  }
}
```

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

```json
{
  "result": {
    "audioUrls": [
      {
        "url": "https://cdn.picsart.com/…/result.mp3",
        "mimeType": "audio/mpeg",
        "driveFile": {}
      }
    ]
  }
}
```

## Additional resources

- Model page: https://picsart.com/api-platform/models/gemini-3.8-flash-tts
- Try it: https://picsart.com/api-platform/models/gemini-3.8-flash-tts/playground
- SDK: https://picsart.com/api-platform/models/gemini-3.8-flash-tts/sdk
- REST API (unified): https://picsart.com/api-platform/models/gemini-3.8-flash-tts/api
- Compatibility API (vendor parameters): https://picsart.com/api-platform/models/gemini-3.8-flash-tts/advanced
- Pricing: https://picsart.com/api-platform/models/gemini-3.8-flash-tts/pricing
- This document: https://picsart.com/api-platform/models/gemini-3.8-flash-tts/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