Fast speech conversion on local systems
Transcribe.cpp is a speech-to-text inference library developed in C++ that supports more than 16 model families. Using the ggml infrastructure, this tool enables different audio processing models to run efficiently on local systems.
Updates
- August 31, 2026: Stars 1,825 → 1,865, latest release v0.2.3 (August 30, 2026).
- August 24, 2026: Stars 1,816 → 1,825, latest release v0.2.2 (August 24, 2026).
- August 20, 2026: Stars 1,802 → 1,816, latest release v0.2.1 (August 20, 2026).
- August 18, 2026: Stars 1,673 → 1,802, latest release v0.2.0 (August 17, 2026).
What you get
- Support for 16 different model families
- High performance on GPU and CPU
- Efficient inference with GGUF format
Installation
# Ubuntu/Debian
sudo apt install build-essential cmake libvulkan-dev glslc libopenblas-dev
cmake -B build -DTRANSCRIBE_VULKAN=ON
cmake --build buildIf you don't write code
I want to convert a local audio file to text using the Transcribe.cpp tool. How can I process my 16 kHz mono WAV format audio file using the transcribe-cli tool compiled on my system and the GGUF format model file I downloaded? Please explain the command structure required for this process and the file paths I should pay attention to.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-21: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.