Frikallo/parakeet.cpp
Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory
This project offers extremely fast and efficient speech recognition directly on devices, particularly Apple Silicon. It takes audio files in various formats (like WAV, MP3, FLAC) and converts them into text, including word-by-word timestamps and speaker identification. This tool is ideal for developers building applications that need real-time or high-volume audio transcription without relying on cloud services or large, complex runtimes.
244 stars.
Use this if you are a developer creating applications that require ultra-fast, on-device audio transcription, speaker diarization, or streaming speech-to-text with minimal latency, especially on Apple Silicon hardware.
Not ideal if you are looking for a ready-to-use application with a graphical user interface or if your primary development environment is not C++.
Stars
244
Forks
7
Language
C++
License
MIT
Category
Last pushed
Mar 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Frikallo/parakeet.cpp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
shibing624/parrots
Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine. 中英语音识别、多角色语音合成，支持多语言，准确率高
altunenes/parakeet-rs
very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust
MainRo/deepspeech-server
A testing server for a speech to text service based on coqui.ai
thewh1teagle/pyannote-rs
pyannote audio diarization in rust
PaddlePaddle/Parakeet
PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS,...