Speech-to-text engines

whisper.cpp

A dependency-free C and C++ port of Whisper under MIT that runs on CPUs, Apple Silicon and phones, with quantised models, an HTTP server and bindings for a dozen languages.

OSIAlternative to Deepgram, AssemblyAI

What it does

whisper.cpp is "high-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model" as a "plain C/C++ implementation without dependencies". It calls Apple Silicon a "first-class citizen", using ARM NEON, Accelerate, Metal and Core ML, and the README says running the encoder on the Neural Engine is more than three times faster than CPU only.

It supports integer quantisation, which the README says makes models need "less memory and disk space" and run more efficiently on some hardware. Its memory table runs from about 273 MB of RAM for tiny to about 3.9 GB for large. GPU paths cover NVIDIA CUDA, Vulkan, AMD ROCm, OpenVINO and several NPUs. The examples include a command-line tool, a stream tool that transcribes from the microphone every half second, and whisper-server, described as an "HTTP transcription server with OAI-like API". Word timestamps and speaker-turn markers exist and are both labelled experimental.

What it replaces

whisper.cpp replaces the Deepgram and AssemblyAI APIs where the hardware is a laptop, a phone or a CPU-only server. Its server speaks an OpenAI-like API, so code written against OpenAI's transcription endpoint can point at it.

Where it falls short: inference only, no training or fine-tuning. The command-line tool takes 16-bit WAV only. Speaker labelling is experimental, and streaming is an example program rather than a supported API.

How it runs

Build with CMake, or use the Docker images (CPU, CUDA, Vulkan variants for linux/amd64 and linux/arm64), Conan, or the npm package. Bindings exist for Rust, JavaScript, Go, Java, Ruby, Objective-C and Swift, .NET, Python, R and Unity. Models are downloaded from Hugging Face in the project's own binary format, converted from OpenAI's MIT weights. On Apple Silicon inference runs fully on the GPU through Metal.

Who it fits

Anyone shipping transcription inside an app, on a Mac, or on a server with no GPU. A team that needs word timestamps and speaker labels in production should look at WhisperX.

Limits the README states

"Limitations: Inference only." The first run with Core ML is slow while the model compiles. Word timestamps, the tinydiarize speaker-turn mode, segment length control and karaoke output are all marked experimental.

Sources

More speech-to-text engines

ProjectReplacesOpennessStarsLast releaseSelf-host
Whisper

OpenAI's general-purpose speech recognition model, released with code and weights under MIT, in six sizes from 39 million to 1.55 billion parameters, with multilingual transcription, translation to English and language detection.

OSI
109,222
Jun 26, 2025
Yes
WhisperX

Batched Whisper transcription under BSD-2-Clause with word-level timestamps from forced alignment and speaker labels from pyannote, the closest open-source match to a hosted transcription API's output.

OSI
24,069
May 25, 2026
Yes
Parakeet (NeMo Speech)

NVIDIA's speech models and toolkit: Apache-2.0 code, and the Parakeet TDT 0.6B v3 model under CC-BY-4.0 with 25 European languages, automatic language detection, punctuation and word timestamps.

Open weights
18,465
Aug 7, 2026
Yes
Vosk

An offline speech recognition toolkit under Apache-2.0 with streaming, models of about 50 MB, 20+ languages, a reconfigurable vocabulary and speaker identification, from small boards to clusters.

OSI
15,131
Apr 22, 2024
Yes
sherpa-onnx

A runtime under Apache-2.0 from the next-generation Kaldi team that runs speech to text, text to speech, speaker diarization and voice activity detection locally on CPUs, NPUs and phones, with no internet connection.

OSI
14,808
Sep 10, 2026
Yes
Moonshine

An on-device speech toolkit under MIT built for live streaming, with speech-to-text models trained from scratch in sizes down to 1 MB, one library across Python, the browser, phones and desktops.

OSI
11,089
Aug 24, 2026
Yes

Added September 16, 2026. Found an error on this page? Write to reveneau@licheo.com and it gets fixed in the next weekly pass.

Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.