v1.0.0 · macOS · Apple Silicon

Your raw video.
Built for YouTube in seconds.

Studio is a native macOS app that automates audio extraction, transcribes with on-device Whisper AI, and drafts SEO-optimized metadata — completely privately, on your Mac.

Download for macOS See how it works

Apple Silicon Optimized
100% Local Transcription
AI Metadata Suite
Free to Use

Studio — Dashboard

v1.0.0

Good evening, Aditya 👋

You have 1 project in progress

Whisper engine active

SPEECH-TO-TEXT98% accurate

00:02

Hey guys, welcome back. Today we are looking at Studio — a fully local macOS app built for video creators.

00:15

By executing transcription entirely on device using Whisper, your raw content remains 100% private.

00:32

Then, local Ollama scans the transcript and shapes our YouTube title, tags, description, and chapters.

AI GENERATED SUITEOllama (Local)

Suggested Title

I Built a Fully Local Video to Text Transcriber! 💻

SEO Description

Drop a video. Get transcripts, titles, descriptions, and chapters on your Mac. Powered by Whisper and Ollama

Generated Tags

#macos#whisper-ai#youtube-seo#on-device

Extract · Transcribe · Publish — Built for efficiency

How it works

Three steps. Zero friction.

The fastest path from raw footage to publish-ready metadata, running fully on your local machine.

Step 1

Import Video

Drop any video format (MP4, MOV, MKV, AVI) straight into the app. Audio extraction happens instantly in the background via local FFmpeg.

Step 2

Local Whisper Transcription

Our embedded Whisper AI engine translates speech-to-text directly on your Apple Silicon Neural Engine. No transcripts or audio ever leave your Mac.

Step 3

AI Metadata & Export

Ollama parses the local transcript to draft high-CTR titles, optimized descriptions, tags, and timestamps. Copy to clipboard and upload to YouTube.

Features

Everything you need to publish.

From raw video file to optimized YouTube dashboard inputs in one window.

Local AI Engine

On-Device Whisper Transcription

Studio embeds whisper.cpp directly inside the macOS sandbox. Speech-to-text runs directly on Apple Silicon M-series chips at zero latency, with absolute privacy. No transcripts, data, or audio files are ever sent to an external server.

AI Titles & Descriptions

Ollama runs locally on your Mac to read your transcript and draft high-CTR titles and SEO-rich descriptions—100% free and using zero API tokens.

Chapters & Timestamps

Studio analyzes the timeline progression to segment your transcript into logical chapters with precise timestamps, ready to copy-paste into YouTube.

AI Thumbnail Concepts

Generate visual concepts for your thumbnails via DALL·E 3, drafting high-clickability image ideas straight from the video transcript context.

Social Multi-Posting

Turn your video into ready-to-post Twitter threads, LinkedIn summaries, or newsletter briefs, extending your content reach with a single click.

Native macOS Sandbox

A premium dark interface designed to look and feel completely native on macOS. Runs fast and stores all models inside system sandbox directories.

FAQ

Questions? Answered.

Is Studio free?

Yes. Studio is completely free to download and use. The on-device Whisper transcription runs at zero cost.

Does it require an internet connection?

Only partially. Video import, audio extraction (FFmpeg), Whisper transcription, and AI metadata generation (Ollama) all work 100% offline. You only need internet when generating thumbnail concepts via OpenAI's DALL-E 3.

What video formats are supported?

Studio uses FFmpeg under the hood, so it supports virtually every video format: MP4, MOV, MKV, AVI, WebM, and more. If FFmpeg can read it, Studio can process it.

How does the AI metadata generation work?

After Whisper transcribes your video, the transcript is processed locally using Ollama on your Mac. It analyzes the content and generates SEO-optimized titles, descriptions, tags, chapters with timestamps, LinkedIn posts, and Twitter threads — completely privately and offline.

Is my data private?

The transcription and AI metadata generation happen entirely on your device using whisper.cpp and Ollama — no data or text ever leaves your Mac. The only optional external API request is to OpenAI for generating thumbnail concepts if you choose to use that feature.

Why does it require Apple Silicon?

Studio is optimized for Apple Silicon's Neural Engine, which enables fast, efficient on-device transcription with Whisper. The app's performance and UI rendering are tuned for M-series chips.

Your raw video.Built for YouTube in seconds.