@GitHub_Daily: MacParakeet is an open-source tool on GitHub designed specifically for Macs that performs purely local speech-to-text transcription with high accuracy. It supports dragging and dropping audio/video files or pasting YouTube links to quickly generate transcripts with timestamps and speaker labels. It can also simultaneously record system audio and microphone input...

X AI KOLs Timeline Tools

Summary

MacParakeet is a new open-source Mac application that provides fast, fully local voice transcription using Apple's Neural Engine and NVIDIA's Parakeet model, ensuring privacy by keeping audio data on-device.

MacParakeet is an open-source tool on GitHub designed specifically for Macs that performs purely local speech-to-text transcription with high accuracy. It supports dragging and dropping audio/video files or pasting YouTube links to quickly generate transcripts with timestamps and speaker labels. It can also simultaneously record system audio and microphone input, allowing you to view real-time transcription while taking notes during meetings. GitHub: http://github.com/moona3k/macparakeet… Speech recognition runs entirely locally, directly leveraging Apple's Neural Engine for high speed, ensuring that audio data never leaves your device. For advanced needs, it can connect to local Ollama or various large language model APIs to automatically generate meeting summaries and format them. It provides a ready-to-use installer package, supporting only Apple Silicon chips. If you are looking for a fast, privacy-first speech-to-text tool, give it a try.
Original Article
View Cached Full Text

Cached at: 05/10/26, 08:24 AM

MacParakeet

Fast voice app for Mac with fully local speech and optional AI. Free and open-source.

There are many voice transcription/dictation apps, but this one is mine.

macparakeet.com

Similar Articles

@NFTCPS: Here’s a macOS terminal tool that cures not understanding English in meetings: Microphone or meeting audio in, real-time captions plus Chinese translation out, no network needed, privacy lovers rejoice. Runs locally on Apple Silicon GPU, English transcription fed directly to Hunyuan MT for Chinese translation. Can also distinguish who’s speaking…

X AI KOLs Timeline

Introduces livecaption, a command-line tool for real-time English transcription and Chinese translation on macOS. It runs locally using Apple Silicon GPU, supports speaker diarization and two-pass correction, no internet required, preserving privacy.

@noahduck283: A tool that can download any YouTube video, cleanly remove vocals, transcribe, translate into 100+ languages, clone the original voice, and perform fully automatic dubbing. It takes less than 2 minutes. 100% runs locally. Free. Sews six top open-source models into a web page for "one-click download, vocal removal, transcription, translation, dubbing"...

X AI KOLs Timeline

Voice-Pro is a web tool that integrates six top open-source models (Whisper, Demucs, CosyVoice, F5-TTS, etc.), supporting YouTube video downloading, vocal removal, transcription, translation, voice cloning, and fully automatic dubbing. It takes less than 2 minutes, runs 100% locally, and is free.

@GitHub_Daily: When writing on a computer, the thoughts in my head are clear, but typing to organize the words is slow. Especially when writing AI prompts — saying it is just one sentence, but when typing, you have to repeatedly adjust the format. Saw OpenLess, an open-source voice input tool on GitHub, which can serve as an open-source alternative to Typeless, Wispr Flo…

X AI KOLs Timeline

OpenLess is an open-source voice input tool that supports macOS and Windows, capable of converting speech to text and automatically polishing it, especially suitable for writing AI prompts.

@uniswap12: Microsoft open-sourced a voice AI that can transcribe 60 minutes of long audio in one go, handling 4 people speaking simultaneously. VibeVoice, open-sourced by Microsoft, 24.8k stars, I only found out about it today. For converting recordings to text, I've been using Whisper, but it often times out on long meeting recordings and struggles with multi-speaker recognition...

X AI KOLs Timeline

Microsoft open-sourced the VibeVoice speech AI framework, which supports one-shot transcription of 60-minute long audio, multi-speaker diarization and timestamp labeling, and also provides multi-role TTS synthesis capabilities. It is based on Qwen2.5 and comes with a 0.5B lightweight real-time version. It has received 24.8k stars on GitHub.

Parrot Speech-to-text API

Product Hunt

Parrot Speech-to-text API offers fast and accurate transcription for production-grade voice agents.