transcribe.cpp

transcribe.cpp: C/C++ speech-to-text inference library that runs diverse STT model families via GGUF models on the ggml runtime.

transcribe.cpp is a C/C++ speech-to-text inference library designed for fast GPU and CPU transcription. It runs diverse STT model families via GGUF models on the ggml runtime, supporting backends like Metal, Vulkan, CUDA, and a tinyBLAS-accelerated CPU path. Input audio must be 16 kHz mono WAV. The library supports numerous model families including Whisper, Canary, Moonshine, Parakeet, and Qwen3-ASR, providing capabilities such as streaming, diarization, translation, and word timestamps. Official bindings are available for Python, TypeScript, JavaScript, Rust, Swift, and Objective-C.

transcribe.cpp at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, CLI, self-hosted, open source
Pricing: Free and open source
Released: April 2026
Category: AI audio tool
Website: github.com/handy-computer/transcribe.cpp

Key features

Run 16 speech-to-text model families
Support Metal, Vulkan, and CUDA GPU backends
Execute streaming and batch transcription
Perform speaker diarization
Translate audio content
Generate word and token timestamps
Convert NeMo checkpoints to GGUF format

Use it for

Transcribe audio files using various STT models
Stream speech-to-text inference in real time
Perform speaker diarization on audio recordings
Translate spoken audio into text

Alternatives to transcribe.cpp

audio.cpp — Runs modern audio models locally with high-performance, native C++ execution.
CTranslate2 — Provides fast and efficient inference execution for Transformer models.
whisper.cpp — It provides high-performance, offline speech recognition on diverse hardware.
faster-whisper — Transcribes audio faster with lower memory usage than standard implementations.
FluidAudio — Runs local audio AI models on Apple Neural Engine.
Speech-to-Speech — Fully modular, swappable components with local or hosted execution options.
WhisperLive — It provides real-time speech-to-text using multiple backends like Faster Whisper and TensorRT.
Free ASR — Zero-dependency real-time streaming speech-to-text with no account login required.
AuK — It handles zero-shot TTS, editing, and enhancement via natural language.
WeNet — Achieves state-of-the-art results on public speech datasets.
AssemblyAI — Industry-leading speech models deliver high accuracy and low latency for voice applications.
kokoro-onnx — Runs local TTS inference with efficient ONNX runtime performance.

All transcribe.cpp alternatives