🔒 100% On-Device & Private AI Speech Recognition

Transcribe & Translate Audio
Directly on Your Machine

MTranscriber brings the power of OpenAI Whisper to a modern, elegant desktop interface. Zero cloud dependencies, zero data collection, and blazing fast local inference.

🛡️ Privacy Promise: Transcriptions are processed locally on your hardware. Audio and transcripts never leave your computer.
MTranscriber — Private On-Device AI Transcriber
Logo
MTranscriber 100% PRIVATE & ON-DEVICE
Local AI inference powered by Whisper. Zero cloud telemetry.
● Hardware acceleration active
1. Model & Translation Language
🧠 Model: Base (~140 MB)
🌐 Target: Română (Romanian)
🎵
interview_recording_q3.mp3
16.4 MB • 44.1kHz Stereo
TIMESTAMPED SEGMENTS (ROMANIAN TRANSLATION) ⏱ 00:34 • 84 words • 3 segments
00:00.000 → 00:04.280 Bun venit la conferința noastră despre tehnologiile de inteligență artificială aplicate local.
📋
00:04.300 → 00:08.750 Toate procesele de recunoaștere vocală rulează direct pe procesorul dumneavoastră fără conexiune cloud.
📋
💾 Export File (.srt / .txt / .vtt / .json)
📋 Copy Text
🚀
MTranscriber v1.0.0
Released September 2026 • Official Build
Changelog & Assets

Engineered for Privacy & Performance

Local neural speech transcription with a zero-compromise desktop experience.

🔒

100% Local & Private

Audio is processed exclusively on your CPU or GPU. No network requests are made during transcription. Temporary audio conversion buffers are sanitized immediately after inference.

🌐

99+ Languages & Romanian

Instantly search spoken languages by name, native script (e.g. Română), or ISO code. Perform post-transcription translation into Romanian and 30+ languages without re-running audio recognition.

🧠

Flexible Whisper Models

Choose between Tiny (~75MB), Base (~140MB), Small (~460MB), and Medium (~1.5GB) depending on your speed and accuracy requirements. You can also import any custom GGML .bin model file.

Hardware Acceleration

Full native bindings to whisper.cpp with Apple Silicon Metal GPU acceleration on macOS and optimized AVX2 SIMD instructions on Windows and Linux.

⏱️

Dual Segment & Text Views

Stream real-time millisecond-precise timestamped chunks ([00:01.200 → 00:05.100]) alongside a clean, consolidated full transcript with real-time word and segment counters.

💾

Consolidated Export Engine

Export your transcripts in one click to SubRip Subtitles (.srt), WebVTT (.vtt), Plain Text (.txt), or structured .json. Quick copy button included.

Getting Started in Seconds

Run MTranscriber on Windows, macOS, or Linux.

🪟 Windows Setup

Download the installer wizard or standalone portable package:

# 1. Download MTranscriber_Setup.exe # 2. Run the wizard installer # 3. Double click desktop icon to launch!

Static FFmpeg is automatically included or installed via 1-click inside the app.

🍎 macOS / Linux Setup

Run natively with .NET 8 on Apple Silicon or Intel:

git clone https://github.com/m-apps-org/mTranscriber.git cd mTranscriber dotnet run

Uses macOS native CoreAudio/afconvert engine with zero extra dependencies required.