Open source

Open-source speech-to-text engines

The models and runtimes behind transcription: Whisper and its faster ports, newer models from NVIDIA and Moonshine, and servers that expose them through an OpenAI-compatible API so existing code keeps working.

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
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.

OSI
53,711
Sep 11, 2026
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
Speaches

An OpenAI-compatible server under MIT for streaming transcription, translation and text to speech, loading Whisper, Kokoro and Piper models on demand, described by its maintainers as Ollama for speech models.

OSI
3,665
Dec 27, 2025
Yes

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.