You get an in-app notification when a new version is published. Nothing is installed or updated on your computer automatically.
What it does
A small TypeScript module that turns a prompt into an image with OpenAI gpt-image-1, or a text into spoken audio with OpenAI tts-1 (six voices, MP3). Every result comes with a cost estimate. Inputs are validated before any paid call, and without a key it returns a clear error instead of fake media. Music generation and the other providers of the original are not included in 1.0.0.
🧪 Try it on MLAIEL
Choose the model before you run. “MLAIEL key (OpenAI)” uses the platform key. Your own OpenAI key, Leonardo and Luma are yours: paste them for this request only. MLAIEL does not save them. Pollinations, when it is offered, is free and needs no key. Inputs and results are checked, nothing you send is stored, and you get 8 tries per day across all tools.
Sign in with a verified email to try this tool. Sign in
Downloads come straight from the source repository. MLAIEL does not host files.
🔌 Integrate
Follow these steps in order. If you get stuck, ask in the improvement project.
Use as a library
import { generateImage, generateSpeech } from "./multimedia-generator/src/index.ts";
const [image] = await generateImage({ prompt: "a red apple", quality: "low" });
const speech = await generateSpeech({ text: "Hello", voice: "nova" });
Command line
node --env-file=.env examples/cli.ts image "a lighthouse at dawn" out.jpg
Works with
Node.js 22.18+ (runs TypeScript directly, no build step) · Windows, macOS, Linux (tested on Windows 11) · No runtime npm dependencies
License
License: MIT
MIT, declared by the owner: Fahed Mlaiel, who holds all rights to Mlaiel/iacherie, chose the MIT License for this clean TypeScript rewrite on 2026-10-01. The package ships the LICENSE file. This is not legal advice.
This is not legal advice. Check the license yourself before you use or share this tool.
Security check
No secrets found in the checked files.
No risky install commands found.
Checked on Oct 1, 2026
How it was tested
Run test · Passed
Windows 11, Node.js 22.18, package 1.0.0 run from source with a real OpenAI key, 2026-10-01 · Oct 1, 2026
Generated an image and a speech file from one prompt with a real OpenAI key; both outputs opened and checked by hand.
npm test passes (package unit tests)
gpt-image-1 returned a JPEG that matches the prompt
tts-1 returned an MP3 that reads the text correctly
Cost estimate reported with each output
Install test · Passed
Windows 11 · CPython 3.12.7 · fresh virtual environment with httpx only · all provider keys removed · Oct 1, 2026
Verified installation — API connection requires your own key.
Import with only httpx installed: passed
Run test · Partly passed
Windows 11 · CPython 3.12.7 · fresh virtual environment with httpx only · all provider keys removed · Oct 1, 2026
Ran without any key: image and voice calls returned an honest error (for example “OPENAI_API_KEY not configured”) and no fake media. No real generation was tested.
generate_image_dalle3 without key → error, no image
generate_voice without key → error
Env name mismatch found: REPLICATE_API_KEY (code) vs REPLICATE_API_TOKEN (README)
Versions and changes
0.1.0 → 1.0.0
Oct 1, 2026 · source revision mlaiel packages/marketplace/[email protected]
1.0.0 is a clean TypeScript rewrite focused on what could be tested end to end: images with gpt-image-1 (DALL·E 3 is no longer available) and speech with tts-1. Stability AI, Replicate, ElevenLabs and Suno were not ported. Validated with the real OpenAI API.
Clean TypeScript rewrite of iacherie multimedia_generation.py.
Images now use gpt-image-1 (DALL-E 3 is no longer available on current accounts).
Speech with tts-1, six voices, MP3 by default.
Input validation before any paid call; cost estimate on every result.
Stability AI, Replicate, ElevenLabs and Suno paths not ported (could not be tested).
0.1.0 · first release
Oct 1, 2026 · source revision 54911be
First listing of the iacherie multimedia module, pinned to the analyzed revision. No code changes compared to the source repository.
Updates are never applied silently. You decide if and when to download a new version.