whisper

jamiepine/voicebox

A local voice studio that clones, dictates, and powers agents — Voicebox bundles cloning, speech generation, and system-wide dictation into one local stack built on Qwen3-TTS and Whisper, with CUDA and MLX support. It's for developers and privacy-minded users who want full voice I/O for apps or AI agents without sending audio to the cloud.

The open-source AI voice studio. Clone, dictate, create.

Zackriya-Solutions/meetily

Rust-powered meeting assistant transcribes and summarizes fully offline — Meetily now runs 4x faster transcription via Parakeet/Whisper with speaker diarization and Ollama-based summarization, built in Rust for macOS and Windows. All processing stays local with no cloud dependency, making it suited for privacy-conscious teams and enterprises needing self-hosted meeting notes.

Privacy first AI meeting note taker. Download Free and open source granola, otter ai, fireflies alternative. Parakeet / Whisper live transcription, on-device speaker diarization, built on Rust. 100% local processing. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker & Assistant for macOS & Windows

m-bain/whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

abus-aikorea/voice-pro

One Gradio UI for TTS, Voice Cloning, Whisper, and Dubbing — Voice-Pro bundles Edge-TTS/Kokoro TTS, zero-shot voice cloning (E2/F5-TTS, CosyVoice), Whisper-based transcription, YouTube download, Demucs vocal isolation, and multilingual translation into one Gradio web app. It targets creators and developers who want an end-to-end pipeline for subtitling, dubbing, and podcast/audiobook production without stitching separate tools together.

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

OpenWhispr/openwhispr

A free, open-source alternative to WisprFlow and Granola — OpenWhispr lets you dictate text anywhere on macOS, Windows, or Linux via hotkey. It supports fully offline transcription with local models (Whisper, NVIDIA Parakeet, Cohere Transcribe) or BYOK cloud processing, with no data collection, positioning it as a privacy-first open alternative to WisprFlow and Granola.

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

TechyCSR/OpenCluely

A stealth AI overlay built as an open-source Cluely alternative for coding interviews — OpenCluely is a free, open-source desktop app for DSA interviews, OAs, and competitive programming. It adds an invisible overlay that stays hidden from Zoom, Meet, Teams, and screen recorders, answering questions in real time via voice or screenshot with streaming, syntax-highlighted code.

OpenCluely is a free, open source Cluely (alternative), built for technical interviews like DSA, OAs, and CP. It offers an invisible overlay, real-time AI help, Smart Image Processing for question capture, and multi-language support : 100% customizable and private.

vincentsch/explainroo

Explainer videos and product demos made by your AI agent. Free and open source: a local voice (Kokoro), word timing (Whisper) and a canvas renderer turn a script into a narrated MP4.

opennookorg/betterwispr

Free, open-source, local-first dictation app for macOS. Hold a shortcut, speak, and text is typed into any app. On-device speech-to-text with Whisper, Parakeet and Apple speech. Private, offline, open-source Wispr Flow alternative.

raullenchai/esp32-thinks

A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.

turantekin/Parrot

A live, on-device AI assistant for your Mac meetings — Parrot records and transcribes calls locally on Apple Silicon, surfacing answers from your own documents while you're still talking rather than only after the meeting ends. No bot joins the call, and the AI backend is your choice: Claude, an OpenAI-compatible server, or a local Ollama model for fully offline use.

Meeting recorder for your Mac with a live AI assistant. On-device transcription, answers from your own docs mid-call. Local-first and open source.

watzon/sayso

Cross-platform dictation that keeps speech recognition on-device — Sayso is a Rust/GPUI dictation app for macOS, Windows, and Linux that pastes transcribed speech into any focused app via a hotkey. It runs local models (Parakeet, Whisper variants, SenseVoice, and more) using WhisperKit, transcribe-rs, or sherpa-onnx, with optional cloud transcription and AI-powered text styling if you add your own API key.

Dictation that runs on your own computer. Press a key, speak, and the text lands in the app you are using. Free and open source, for macOS, Windows, and Linux.