Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Instant dictation app for Mac

A SoundCloud player in your terminal

very fast speech-to-text (even in CPU) with NVIDIA Parakeet in Rust

Effortless Push-to-Talk Transcription, Anywhere.

一个基于 NVIDIA Parakeet-tdt-0.6b 模型的本地语音转录服务。它提供了一个与 OpenAI API 兼容的接口和一个简洁的 Web 用户界面

🎙️ P³: Lightning-fast podcast processing with Apple Silicon optimization and local LLMs. Parakeet MLX transcription + Ollama analysis = structured podcast summaries in minutes. 100% local, no API keys required.

Real-time offline speech-to-text transcription script on macOS using parakeet-mlx

an easy to use English Text To Speech tool

Parakeet MLX is a next-generation automatic speech recognition (ASR) engine optimized for Apple Silicon (M1/M2/M3), leveraging Apple’s MLX framework for ultra-fast, low-latency transcription. It offers real-time streaming, advanced audio processing. Including noise reduction and silence detection

PaddlePaddle深度学习框架课程、使用笔记

一个基于 NVIDIA Parakeet-tdt-0.6b 模型的docker本地部署语音转录服务。它提供了一个与 OpenAI API 兼容的接口

LiveKit STT plugin for NVIDIA NeMo Parakeet and Canary models

Find out where any sigil (or item) drops in Granblue Fantasy: Relink

A HTML/CSS/JS game about a parakeet (budgerigar)

A desktop application built using the TINS paradigm for transcribing audio files into timed text and previsualization.

A FastAPI wrapper for NVIDIA's new parakeet TTS model designed for high-quality English speech recognition

Multimedia context generation tool using off-the-shelf components. Leverages several local ML/AI tools to accomplish transcription, context clues, and llm-driven tasks. Designed with extensibility in mind. Dataset preparation tool. Adds context to video and audio inputs.

A production-ready, high-performance Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) system using NVIDIA Parakeet for voicemail detection and response generation. Designed to handle 30k-45k+ calls per hour with real-time processing capabilities.

A professional real-time audio transcription system using NVIDIA's Parakeet TDT 0.6B V2 model with advanced voice activity detection and intelligent sentence grouping.