Projects sharing features with VoiceInk

Buzz is a desktop application that provides a local speech-to-text engine for transcribing and translating audio and video files. By leveraging local machine inference, the software ensures data privacy and offline performance, removing the need for cloud connectivity during media processing. The application distinguishes itself through a modular plugin architecture that allows for the integration of custom functionality, such as content summarization and automated text formatting, without modifying the core codebase. It also features a speaker diarization pipeline that identifies and labels

Local speech-to-text for macOS on-device AI, fully private, optional cloud

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Omnilingual-ASR is a multilingual automatic speech recognition framework and toolkit designed to transcribe audio across 1,600 languages. It provides a complete pipeline for converting speech to text, including a toolkit for fine-tuning pre-trained speech models to specific languages or datasets using custom training recipes. The system supports zero-shot speech recognition, allowing the model to predict text in unseen languages without extensive training data. It further enables few-shot language guidance through in-context examples and uses language codes to constrain transcription output t

Cactus is an on-device AI inference engine designed for executing large language models, vision models, and speech-to-text systems on mobile and wearable hardware. It provides a programmable tensor computation graph for defining sequences of matrix operations and activation functions, alongside a local retrieval augmented generation framework that grounds model responses using local text files. The project features a multiplatform SDK with language bindings for integrating AI capabilities into mobile applications and a model conversion system that transforms external model formats for optimiz

This project is a framework for building local voice assistants and a real-time audio streaming server. It functions as a containerized inference engine and a multilingual speech pipeline that orchestrates speech-to-text, language models, and text-to-speech components to convert spoken input into spoken output. The system is distinguished by its use of WebSocket-based bidirectional streaming for low-latency interactions. It features a voice activity detection system that manages speech boundaries and handles user barge-in interruptions during assistant playback. It also supports custom voice

FunASR is an automatic speech recognition toolkit and multilingual speech-to-text engine designed to convert spoken audio into written text across more than fifty languages. It provides a framework for speaker diarization, an OpenAI-compatible transcription API for local server hosting, and speech models compatible with the ONNX format. The project distinguishes itself by supporting high-performance inference on edge hardware via self-contained binaries and portable model exports. It incorporates specialized capabilities for natural speech generation with adjustable timbre and emotional expre

This project provides a self-hosted server for automatic speech recognition, functioning as a containerized inference engine for the Whisper model. It exposes core transcription and translation capabilities through a standardized web interface, allowing for the integration of speech-to-text services into external applications. The service distinguishes itself by incorporating advanced audio analysis tools, including speaker diarization to attribute text to specific individuals and voice activity detection to filter non-speech segments. It supports automated language detection and provides out

This platform serves as a comprehensive environment for managing private language models, document knowledge bases, and automated agent workflows within secure local infrastructure. It functions as a document-aware workspace that enables users to ingest diverse file formats into searchable repositories, ensuring that all data processing and model inference remain within private, local environments to maintain data sovereignty. The system distinguishes itself through a modular agentic engine that allows for the definition of custom skills and external tool execution. By utilizing a multi-model

Nerd-dictation is a command-line utility that provides offline speech-to-text transcription and system-wide desktop automation. It functions as a local recognition engine, processing microphone audio streams directly on the host machine without requiring cloud connectivity or external network services. The tool distinguishes itself by integrating transcription directly into the desktop environment through system-level input injection, which simulates keyboard events to type recognized speech into active application windows. It supports grammar-constrained decoding, allowing users to define sp

WhisperX is an automated speech recognition toolkit designed to convert spoken audio into text while maintaining precise synchronization with the original media. It functions as an integrated pipeline that combines transcription, phoneme-based alignment, and speaker diarization to produce structured, attributed transcripts. The project distinguishes itself through its use of forced alignment, which matches existing text to audio signals at the phoneme level to generate accurate word-level timestamps. It also incorporates speaker diarization to identify and label unique voices within a recordi

Handy is a local speech-to-text automation tool designed to convert spoken audio into text and inject it directly into active desktop applications. By running machine learning models entirely on the host hardware, it provides a private, offline-first environment for dictation and command execution. The system functions as a background service that manages microphone input, transcription state, and text output, enabling hands-free typing across various software environments. The project distinguishes itself through a modular pipeline that integrates local language models for post-transcription

Hold Fn key, speak, paste transcribed text. macOS menu bar app.

Epicenter is a local-first knowledge management system and data orchestrator designed to structure information generated by large language models into validated schemas. It functions as a storage architecture that persists application data in human-readable files and databases to ensure user ownership and portability. The system distinguishes itself by projecting language model outputs into structured, schema-validated tables and utilizing conflict-free replicated data types to synchronize application state across multiple devices without a central server. This allows for offline access and c

Mac-native dictation that just works – lives in the notch, zero setup, free forever

macOS native voice input for Crypto AI professionals — offline ASR, domain vocabulary, implicit learning

Your personal voice interface for any app. Speak naturally and your words appear wherever your cursor is, with fully customizable AI voice dictation. Open source alternative to Wispr Flow.

Open-source AI voice typing for macOS, Windows, and Linux. Press a hotkey, speak naturally, get polished text in any app.

DeepSpeech is an open-source speech-to-text framework and machine learning engine designed to convert spoken audio into written text locally on a device. It provides on-device speech recognition that operates without requiring an internet connection to external servers. The system supports real-time speech transcription across a variety of hardware platforms, ranging from single-board computers and edge devices to GPU servers. This allows for audio analysis and processing directly on the local hardware.

Sherpa-ONNX is an ONNX-based speech processing toolkit that provides a local speech recognition engine, an on-device voice synthesis tool, and a speaker identification framework. It is designed as a cross-platform speech API that enables speech-to-text, text-to-speech, and speaker verification tasks to be executed locally on a device without requiring network access. The project is distinguished by its ability to perform zero-shot voice cloning and speaker diarization on-device. It supports a wide range of hardware accelerations, including GPU and various NPU architectures, and provides a Web

OpenSkills is an agent capability orchestrator and skill manager designed to sync, version, and distribute standardized skill definitions across autonomous agent environments. It functions as a system for installing domain-specific instruction sets and specialized knowledge into large language model agents, acting as a context injector to load task-oriented prompts and technical documentation into an agent's active operational window. The project distinguishes itself through a git-based distribution framework, allowing agent capabilities to be fetched and updated from remote version control s

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve

AI-Media2Doc is a self-hosted media transcription and content repurposing platform. It converts audio and video files into structured documents, searchable transcripts, and notes using a local speech-to-text pipeline and language model integration. The system enables the creation of illustrated articles by extracting video frames based on subtitle timestamps. Users can control the style and structure of generated text through custom behavioral prompts and integrate external language models via configurable API endpoints. The platform covers automated speech transcription, multimedia content

This project is a headless large language model inference engine and server manager designed for local deployments. It provides a developer toolkit and API gateway that allows for the management of model lifecycles and inference tasks without a graphical user interface. The system enables the deployment of model engines across different operating systems, cloud environments, or CI pipelines. It includes a command-line interface for bootstrapping development projects and automating the orchestration of loading and unloading model binaries based on specific workflow needs. The toolset covers i

BiliNote is a tool that converts video URLs into structured, organized notes. It works by extracting video content and metadata from major platforms, transcribing audio to text entirely on-device using a local speech recognition model, and then summarizing the transcript with a language model to produce clean notes that can include screenshots and timestamp links. What sets BiliNote apart is its configurable AI backend, which lets you choose and switch between different language model providers for generating summaries. All transcription happens offline and locally, preserving privacy and ena

Cheetah is an LLM technical interview assistant composed of a native macOS application and a browser extension. It provides real-time coding and answering suggestions during technical interviews by combining live audio transcription with web-based context extraction. The system functions as a real-time interview coach that converts spoken questions into text using on-device speech-to-text processing. It uses a browser-integrated DOM scraper to extract live code and console logs, allowing the AI to analyze the current coding state and generate technical solutions based on the specific environm

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.