MLAIEL

MLAIEL is in test & preview — some profiles and content are demonstrations. Learn more

Audio Studio

Studio

Text-to-speech, transcription and translated voice-over in one place.

Studio = several agents + tools working together.

Ready to UseVersion 1.0.0Published by @Mlaiel6 followers

Staff ran it and it worked. You still need your own provider accounts where listed.

🧪 Try it⬇️ Download🔌 Integrate🧾 View source🔔 Sign in to get updates

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 standalone voice workspace. Turn text into natural speech, transcribe a recording back into text, or translate a text and have the translation read aloud. Text going in and transcripts coming out are moderated. It builds on the Multimedia Generator, Language Detection & Translation and Multilingual Moderation agents.

🧪 Try it on MLAIEL

Runs on MLAIEL's own OpenAI key for signed-in members with a verified email. Inputs and results are moderated, nothing you upload is stored, and you get 8 tries per day across all tools.

Sign in with a verified email to try this tool. Sign in

GitHub activity

mlaiel/iacherie

This repository is linked. Activity appears after the next daily check.

Public data from GitHub, checked once a day.

Who it's for

Creators, educators and developers who need voice-overs, transcripts or multilingual audio.

What it can do

  • Text-to-speech with six OpenAI voices (MP3)
  • Transcription of mp3, m4a, wav, webm, ogg, flac and aac (gpt-4o-mini-transcribe)
  • Translated voice-over: translate, then read aloud
  • Language of the transcript detected offline
  • Moderation of spoken text and transcripts

What's inside this studio

  • Audio Studio Studio
    • Multimedia Generator AgentOpen listing

      speech

    • Language Detection & Translation AgentOpen listing

      voice-over translation

    • Multilingual Moderation AgentOpen listing

      text checks

    • gpt-4o-mini-transcribe Tool

      speech to text

What you need

  • Needs your own OpenAI account

    Put your key in a setting named OPENAI_API_KEY on your own computer. Never share it. Where to get a key

MLAIEL does not run these tools for you and never asks for your provider keys. You run them on your own computer or server, with your own accounts.

How to use it

Install

  1. Install Node.js 22.18 or newer.
  2. Download the 1.0.0 package below and unzip it, then open the audio-studio folder.
  3. Run: npm install && npm test (offline tests, no key needed).
  4. Copy .env.example to .env and add your own OpenAI key (BYOK). Never commit .env.

Use

  1. Speak: node --env-file=.env examples/cli.ts speak "Welcome to MLAIEL" welcome.mp3
  2. Transcribe: node --env-file=.env examples/cli.ts transcribe welcome.mp3
  3. Voice-over: node --env-file=.env examples/cli.ts voiceover fr "Welcome to MLAIEL" bienvenue.mp3
  4. Or click Try it on this page.

⬇️ Download

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 { speak, transcribe, voiceOver } from "./audio-studio/src/index.ts";

const vo = await voiceOver({ text: "Welcome", targetLanguage: "es" });
console.log(vo.translation, vo.speech.mime);

Command line

node --env-file=.env examples/cli.ts voiceover de "Welcome to MLAIEL" willkommen.mp3

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

    Ran speak, voiceover and transcribe with a real OpenAI key; MP3 outputs played back and the transcript matched the audio.

    • npm test passes (package unit tests)
    • speak: tts-1 MP3 reads the text with the chosen voice
    • voiceover: script rewritten and narrated to MP3
    • transcribe: whisper-1 transcript matches the spoken audio

  • Code check · Partly passed

    Windows 11 · CPython 3.12.7 · fresh virtual environment with httpx only · all provider keys removed · Oct 1, 2026

    Imports only with the whole iacherie project on the Python path; it logs missing libraries. No audio was generated.

    • Import inside full tree: succeeded with warnings
    • Standalone import: not possible
    • Generation: not attempted

Versions and changes

  • 0.1.0 → 1.0.0

    Oct 1, 2026 · source revision mlaiel packages/marketplace/audio-studio@1.0.0

    1.0.0 is the first standalone version: it no longer needs the full iacherie project. Text-to-speech, transcription and translated voice-over with moderation. Coqui TTS and ElevenLabs were not ported. Validated with the real OpenAI API.

    • First standalone version: no longer needs the full iacherie repository.
    • Text-to-speech (tts-1), transcription (gpt-4o-mini-transcribe) and translated voice-over.
    • Moderation of spoken text and transcripts; transcript language detected offline.
    • Coqui TTS and ElevenLabs paths of the original not ported.

  • 0.1.0 · first release

    Oct 1, 2026 · source revision 54911be

    Listing of the iacherie Audio Studio as found at revision 54911be. Not runnable on its own yet.

Updates are never applied silently. You decide if and when to download a new version.

Help improve it

Open the project “Audio Studio — Continuous Improvement”

Source files: core/content/audio_studio.py

← Back to the marketplace