mirror of
https://github.com/HeyPuter/puter.git
synced 2026-11-05 21:46:51 +00:00
242a654166
* feat(ai): add Kling for video, image and speech generation One `kling` API key now registers a provider on three drivers: - txt2vid: Kling 3.0 Turbo, 3.0, 3.0 Omni, O1, 2.6 and 2.5 Turbo, with first/last frames, reference images on the omni models, native audio, and editing a source video on 3.0 Omni and O1. Billed per second at the resolution, audio and video-input rate; an edit is held at the longest source and billed for the clip Kling returns. - txt2img: Kling Image 3.0, 3.0 Omni, O1 and 2.1, billed per image. - txt2speech: Kling TTS with its English and Chinese voices, billed per request. Kling's business error codes map onto the driver error contract, so an exhausted resource pack reports as credit exhaustion and a submit-time content block as `moderation_flagged`. "Risk control" failures now count as content-filter refusals. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai): treat Kling's unknown-model codes as a Puter-side failure Kling answers 1202/1203 when the method or model isn't one it serves. Puter picks both, so these meant catalog drift but surfaced as a 400 that blamed the caller and raised no alarm. They now return 502 upstream_failed with a warning alarm. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(ai): tighten Kling input checks and error mapping - 3.0 Turbo takes at most 2,500 prompt characters with a first frame, the image-to-video endpoint's limit. - O1 refuses reference images together with a first and last frame. - 3.0 Omni accepts a source of up to 15.5 seconds, and an edit is held at 16 seconds to cover it. - A source video Kling can't decode fails as 400 upstream_bad_request instead of a Puter-side 502. - A 1201 about the model counts as catalog drift, like 1202/1203. - Auth failures no longer pass Kling's console wording to the caller. Adds integration tests for the image, video and TTS providers, gated on PUTER_TEST_AI_KLING_API_KEY. * feat(ai): wait up to 14 minutes for a video job Video jobs, Kling edits in particular, can take over 10 minutes. The poll window and the Gemini Omni deadline move to 14 minutes, under the SDK's 15-minute idle timeout, with holds and signed source links lengthened to match. The keep-alive default moves to 920 seconds so it stays above a 15-minute proxy idle timeout. --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Daniel Salazar <daniel.salazar@puter.com>
Puter.js
Learn More · Docs · Tutorials · Examples · X
Puter.js gives you auth, cloud storage, database, AI, and more through a single JavaScript library. It is the go-to backend for AI-generated apps.
There is nothing to configure, no API keys, no infrastructure to set up, whether you write the code yourself or have your AI tool do it. Tools like Claude Code, Codex, OpenCode, Lovable, and Replit can generate complete, production-ready apps in a single shot with fewer AI tokens.
Installation
NPM:
npm install @heyputer/puter.js
CDN:
Include Puter.js directly in your HTML via CDN in the <head> section:
<script src="https://js.puter.com/v2/"></script>
Usage
Browser
ES Modules
import {puter} from '@heyputer/puter.js';
// or
import puter from '@heyputer/puter.js';
// or
import '@heyputer/puter.js'; // puter will be available globally
CommonJS
const {puter} = require('@heyputer/puter.js');
// or
const puter = require('@heyputer/puter.js');
// or
require('@heyputer/puter.js'); // puter will be available globally
Node.js (with Auth Token)
const {init} = require("@heyputer/puter.js/src/init.cjs"); // NODE JS ONLY
// or
import {init} from "@heyputer/puter.js/src/init.cjs";
const puter = init(process.env.puterAuthToken); // uses your auth token
const puter2 = init(process.env.puterAuthToken2); // use some other auth token
Node.js (with Auth Token + Web Login)
const {init, getAuthToken} = require("@heyputer/puter.js/src/init.cjs");
// or
import {init, getAuthToken} from "@heyputer/puter.js/src/init.cjs";
const authToken = await getAuthToken(); // performs browser based auth and retrieves token (requires browser)
const puter = init(authToken); // uses your auth token
Usage Example
After importing, you can use the global puter object:
// Print a message
puter.print('Hello from Puter.js!');
// Chat with GPT-5 nano
puter.ai.chat('What color was Napoleon\'s white horse?').then(response => {
puter.print(response);
});
Starter Templates
You can also use one of the following templates:
- Client-side projects: Angular, React, Next.js, Vue.js, Vanilla.js
- Node.js + Express: Node.js + Express template
Setting Custom Origins
By default puter.js uses the official Puter API and GUI origins. You can customize these origins by setting global variables before importing the SDK like so:
// For API origin
globalThis.PUTER_API_ORIGIN = 'https://custom-api.puter.com';
// For GUI origin
globalThis.PUTER_ORIGIN = 'https://custom-gui.puter.com';
import {puter} from '@heyputer/puter.js'; // or however you import it for your env
Documentation & Community
License
Apache-2.0