Recentech StudioRecentech Studio

AI Visual & Media Tools

Create mind maps, generate charts, extract text from images, convert text to speech, and convert image formats. Five powerful visual and media tools — all free to use.

AI-PoweredFree to Use5 Tools in One

Available Tools

AI Chart Creator

Generate professional data visualizations, bar charts, line charts, pie charts, and diagrams from your data descriptions.

AI Image OCR

Extract text from images, screenshots, scanned documents, and photos using AI-powered optical character recognition.

Text-to-Speech

Convert any text to natural-sounding audio using browser speech synthesis. Choose voices, adjust speed, and listen instantly.

Image Converter

Convert images between PNG, JPEG, and WebP formats. Fast, private, and runs entirely in your browser.

Try the Visual & Media Tools

Text to Convert
Enter the text you want to convert to speech (max 5000 characters)
~0 sec0 words
0 / 5000 characters
Try an example:
Voice Engineruns on your device
HD neural voices
86 MB once

Kokoro-82M neural model — most natural quality and real WAV export. 53 voices across 9 languages.

Checking local model cache…

Speed

⚠️ AI may produce inaccurate information. Please verify important details.

Key Features & Benefits

HD Neural Voices — Kokoro-82M

53 real neural voices across 9 languages: English (US/UK), Spanish, French, Italian, Portuguese (Brazil), Hindi, Japanese, and Chinese. The model runs entirely in your browser — no server, no API.

One-Time Download, Only When You Ask

The voice model (~86 MB) is never downloaded automatically. You press the download button, it saves into your browser cache once, and from then on every generation happens on your device.

100% Private — On-Device AI

Everything runs on your device. Your text never touches a server — no API calls, no tracking, no data collection. What you type stays with you.

Download Real Audio (WAV)

Export the actual generated sound as a WAV file — ready for video voiceovers, podcasts, or study material. The audio is truly generated on your hardware.

Real Speech Markup

Only markup that genuinely works: [pause:1s] inserts a real second of silence, [slow] and [fast] really change the pace of that section. Long texts are split into sentences and merged into one smooth file.

Free — No Credits, No API Keys

Like the other on-device labs, this tool costs 0 credits. The neural model is Apache-2.0 licensed and runs on your hardware — no sign-ups, no per-character billing, no server costs.

Full Playback Controls

Play, pause, and stop with a progress bar that tracks the real audio position of the generated file.

Works Offline After Setup

Once the model is cached in your browser, the tool works offline. You can remove the cached model anytime with one click from the Voice Engine card.

Frequently Asked Questions

How does Text-to-Speech work?
It runs the Kokoro-82M neural model inside your browser via WebAssembly. Press 'Download voice model' once (~86 MB, stored in your browser cache) — from then on every generation happens on your device, with real WAV export.
Is my text data stored or sent anywhere?
No. Everything processes locally in your browser. Your text is never sent to any server, never stored, and disappears when you close the page.
Why does the tool need a one-time download?
A neural voice model is a large file — about 86 MB. It is only downloaded when you press the download button; nothing downloads automatically or in the background. It is saved in your browser cache (nothing is installed on your computer), works offline afterwards, and you can remove it anytime from the Voice Engine card.
How do I remove the model from my device?
Open the Voice Engine card and click 'Remove cached model'. The model files are deleted from your browser cache immediately — nothing remains on your computer.
How fast is generation?
Faster than real time on computers with WebGPU; on CPU-only devices a 10-second clip typically takes 10–60 seconds, with a live progress indicator throughout.
Can I download the audio?
Yes — every generation can be saved as a real 24 kHz WAV file, ready to use anywhere.
Which languages are supported?
Kokoro-82M supports 9 language groups: English (US/UK) at the highest quality, plus Spanish, French, Italian, Portuguese (Brazil), Hindi, Japanese, and Chinese — 53 real voices grouped by language. This tool does not read or use the voices installed on your device.
Does this cost credits?
No. Like the other on-device labs, this tool is completely free: it runs on your hardware, so there are no server costs to cover — no credits, no API keys, no usage limits.
Upload Images

Click or drag images

PNG, JPEG, WebP, GIF, BMP

Output Format
Images (0)

No Images Yet

Upload images to get started

Drag & Drop Ctrl+V
Smart Compression
92%

Background Removal

Corner-color detection, in your browser

Image Upscaler

Enlarge with bicubic interpolation

EXIF metadata

Removed by default — your choice

Conversion re-encodes the image from raw pixels in your browser, so EXIF metadata — GPS location, camera model, timestamps, software tags — is permanently removed from the output. Turn the switch ON to keep the original EXIF in JPEG output when the source is a JPEG. Files are never uploaded to any server.

Key Features & Benefits

Multi-Format Conversion

Convert between PNG, JPEG, WebP, GIF, BMP, and ICO. GIF and BMP are encoded by our own in-browser encoders with a real 256-color palette and LZW compression, and ICO exports a proper favicon file capped at 256x256. Every output file is the real format it claims to be.

Smart Compression

Set a target file size and the tool automatically iterates quality (JPEG/WebP) or dimensions (PNG/GIF/BMP/ICO) toward it — reaching the target or getting as close as the format allows. Or use presets for Web, Email, Social Media, and Print. The result is always a real file in your chosen format.

Background Removal

Corner-color detection runs instantly in your browser: it samples the four corner colors and makes similar pixels transparent. Works best on solid backgrounds like white or green screen — and it will tell you that honestly instead of pretending to be AI.

Image Upscaler

Enlarge images 2x, 3x, or 4x using high-quality canvas bicubic interpolation — entirely in your browser. This is real interpolation, not AI invention: the output is a larger version of your exact image.

EXIF Metadata — Your Choice

EXIF metadata is removed by default: conversion re-encodes the image from raw pixels, so GPS location, camera model, and timestamps never survive. Converting a JPEG photo to JPEG and want to keep the camera data? Flip the 'Keep EXIF' switch and the original EXIF block is copied into the output — all on your device.

Batch Processing

Upload and convert multiple images at once. Set format, quality, and size settings once and apply to all images. Download individually or convert all at once, with real progress per file.

100% Private, On-Device Processing

All image processing — conversion, filters, background removal, upscaling — happens entirely in your browser. Images never leave your device, and the tool works like the built-in labs: no credits, no uploads, no tracking of your files.

Frequently Asked Questions

What image formats can I convert between?
PNG, JPEG, WebP, GIF, BMP, and ICO — all encoded for real in your browser. GIF output is a genuine GIF89a file with an image-derived 256-color palette (single frame, no animation). BMP is a standard 24-bit file. ICO uses a PNG-compressed entry capped at 256x256, which is the format spec maximum and works for favicons. AVIF is not offered because honest AVIF encoding requires a heavy WASM encoder — we chose not to fake it.
How does Smart Compression work?
For JPEG and WebP, the tool iteratively lowers the quality parameter toward your target file size. For PNG, GIF, BMP, and ICO — which ignore the quality parameter — it gradually reduces dimensions instead, as far as it can. Either way you get a real file in the format you asked for.
How does Background Removal work?
It samples the colors at the four corners of your image, then makes every similar-colored pixel transparent with smooth edge transitions. It is a real, instant, on-device algorithm — but it has honest limits: it works best on solid or uniform backgrounds (white, green screen) and will only partially remove busy or gradient backgrounds. Save as PNG or WebP to keep the transparency.
What does the Image Upscaler actually do?
It enlarges your image 2x, 3x, or 4x using the browser's high-quality bicubic interpolation. This is real interpolation — your image, bigger — not AI detail invention. It works entirely on your device and is great for preparing images for larger displays.
What about EXIF data and privacy?
EXIF is removed by default: conversion re-encodes your image from raw pixels in the browser, so GPS coordinates, camera model, dates, and software tags never survive. If you want to keep it, turn on 'Keep EXIF metadata' in the Metadata Privacy section — when the source is a JPEG with EXIF and the output is JPEG, the original EXIF block is copied straight into the converted file. PNG, WebP, and other outputs are always metadata-free, and your images are never uploaded to any server.
Can I resize images before converting?
Yes! You can resize by percentage or enter custom dimensions. The aspect ratio lock ensures your image doesn't get distorted. Preset sizes for common use cases (social media, web, thumbnails) are also available.
Does this tool cost credits?
No. Like the built-in labs, the Image Converter runs entirely on your device and costs nothing. There is no account requirement, no server processing, and no credit consumption — the only limit is your own hardware.
What if my image format won't load?
The tool only accepts images your browser can actually decode (JPEG, PNG, WebP, GIF, BMP, AVIF inputs, depending on your browser). If a file can't be decoded — for example TIFF or HEIC — it is rejected with a clear message instead of producing a broken conversion.

Visual & Media Tools – Frequently Asked Questions

Common questions about the AI visual and media tools in Recentech Studio.

What visual and media tools are available?
Recentech Studio offers five visual and media tools: AI Mind Map Generator (create interactive mind maps from any topic), AI Chart Creator (generate data visualizations and diagrams), Text-to-Speech (convert text to natural-sounding audio), AI Image OCR (extract text from images and screenshots), and Image Converter (convert between PNG, JPEG, WebP, and more).
Can I create mind maps for free?
Yes, the AI Mind Map Generator is free to use. Enter any topic and the AI creates a structured, interactive mind map with branches and subtopics. Daily usage limits apply.
How does the Image OCR work?
Upload any image containing text (screenshots, scanned documents, photos of text) and the AI OCR tool will extract and describe the text content. It supports PNG, JPEG, and WebP formats and can handle multiple languages.
Is Text-to-Speech free?
Yes, the Text-to-Speech tool is free and runs entirely in your browser using the Web Speech API. You can choose from available voices, adjust speed, and play the audio directly. No server processing is required.
What image formats does the converter support?
The Image Converter supports conversion between PNG, JPEG, and WebP formats. You can upload an image in any supported format and convert it to another. The tool runs entirely in your browser for privacy and speed.