GoogleGemini 3.8 Flash TTSText → Speech

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

Multilingual30 VoicesMulti-SpeakerStyle Direction

Playground SDK API Advanced Usage Pricing

Install the SDK

The SDK targets Node 20+ and ships with TypeScript types.

npm install @picsart/ai-sdk

Authenticate

Create a client once with your API key — it's sent as a bearer token on every request.

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

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
  apiUrl: 'https://api.picsart.com',
});

Run the model

Call the model with its parameters. This example uses the required ones.

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

Parameters

7 parameters. Required ones must be supplied; the rest fall back to their defaults. The API takes these same names over HTTP.

Parameter	Type	Required	Default	Details
`language` Language	`text`	no	`—`	—
`accent` Accent	`text`	no	`—`	—
`prompt` Prompt	`text`	no	`—`	max 6000 chars
`voiceId` Voice	`catalog`	no	`Kore`	options from gemini/v1/catalog/voices
`style` Style	`text`	no	`—`	max 500 chars · e.g. "e.g. warm, unhurried; a bedtime story"
`parts` Spoken Parts	`object`	no	`—`	{ text, speaker, style }
`multiSpeakerVoiceConfigs` Speakers	`object`	no	`—`	{ speaker, voiceName }

Output

generate() resolves once the job completes. An audio URL.

Result

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