Tools

Resonant

Private voice dictation app for Mac that converts speech to text with 100% offline processing. Uses on-device AI to transcribe voice input across any Mac application while keeping all data completely local and secure.

www.onresonant.comFree5mo ago

Handy

Handy is a free, open-source speech-to-text desktop app that lets you dictate into any text field using a keyboard shortcut. Press and hold to speak, release to transcribe — no cloud, no subscription, just local voice-to-text wherever your cursor is. It works across platforms and keeps your voice data private on your own machine.

handy.computerOpen Source1mo ago

Superwhisper

Superwhisper is an AI-powered voice-to-text app for macOS, Windows, and iOS that lets you dictate into any app or website using a simple keyboard shortcut. It supports 100+ languages, works offline and in the cloud, and includes custom AI modes that can reformat your speech into polished, context-appropriate text. It's designed for fast-moving professionals who want to write faster without touching a keyboard.

superwhisper.comFreemium29d ago

Wispr Flow

Wispr Flow is an AI-powered voice dictation app that converts natural, messy speech into clean, polished text across every app on your device. It works 4x faster than typing and is available on Mac, Windows, iPhone, and Android. It's designed for professionals who want to write, code, message, and create at the speed of thought.

wisprflow.aiFreemium29d ago

Almond

Offline dictation software for Mac that converts speech to text locally on your device without requiring an internet connection. It automatically cleans up filler words, learns your vocabulary, and adjusts writing style based on the app you're using.

www.almondvoice.comPaid5mo ago

Aqua Voice

Aqua Voice is a real-time, AI-powered speech-to-text tool for Mac, Windows, and iPhone that converts your voice into clean, accurate text at up to 230 WPM. It works across all your apps without setup, understands technical language like code syntax and framework names, and is built for developers and power users who want to ditch the keyboard. Think of it as a smarter, faster alternative to typing — especially useful for AI prompting and long-form writing.

withaqua.comFreemium29d ago

Winpepper

Windows-native local dictation. Hold a hotkey, speak, release — cleaned-up words appear in the focused app. Parakeet TDT v3 ASR + LlamaSharp cleanup, all local.

https://github.com/obra/winpepperOpen Source2mo ago

Stage Whisper

macOS menu bar app for transcribing speech to text with WhisperKit and inserting it at the cursor, by Jesse Vincent (obra).

https://github.com/obra/stagewhisperOpen Source2mo ago

MacWhisper

Native Mac app for OpenAI Whisper transcription. On-device, drag-and-drop audio/video, 100+ languages.

goodsnooze.gumroad.comFreemium3mo ago

Yakety

Voice recording and transcription app written in C.

https://github.com/badlogic/yaketyOpen Source2mo ago

Pepper X

GNOME-first local Linux dictation utility inspired by Ghost Pepper.

https://github.com/obra/pepper-xOpen Source2mo ago

Simple Meeting Scribe

Personal, 100% local meeting transcriber for macOS built on Whisper and MLX.

https://github.com/czlonkowski/simple-meeting-scribeOpen Source2mo ago

Whisper.spm

Drop whisper.cpp speech-to-text into iOS or macOS apps as a Swift Package Manager dependency, no manual build steps.

https://github.com/ggerganov/whisper.spmOpen Source2mo ago

VibeVoice

Open-source voice AI framework that includes advanced speech recognition (ASR) for 60-minute audio transcription with speaker diarization, text-to-speech (TTS) for 90-minute multi-speaker synthesis, and real-time streaming TTS. Operates at ultra-low 7.5Hz frame rate for efficient long-form audio processing.

github.com/microsoft/vibevoiceOpen Source3mo ago

sag

A command-line text-to-speech tool that mimics macOS's 'say' command but uses ElevenLabs' modern AI voices. It streams audio to speakers by default and supports voice selection, speed controls, and file output.

sag.shOpen Source1mo ago

Subtitler

Free on-device web app for transcribing audio and rendering subtitles — runs in the browser via WASM, nothing leaves your machine.

github.com/dmtrkovalenko/subtitlerOpen Source2mo ago

Voicebox

Open source voice cloning desktop application that lets you clone any voice from just 3 seconds of audio and generate natural speech locally. Features multi-voice project composition, audio effects, and support for multiple TTS engines with complete privacy.

voicebox.shOpen Source5mo ago

PaddleSpeech

Easy-to-use speech toolkit from Baidu's PaddlePaddle — ASR, TTS, speaker verification, and speech translation in one library.

https://github.com/paddlepaddle/paddlespeechOpen Source2mo ago

EspeakNG-Swift

Swift bindings for espeak-ng — embed open-source text-to-speech directly in iOS and macOS apps without cloud round-trips.

github.com/blaizzy/espeakng-swiftOpen Source2mo ago

MegaTTS3

ByteDance's open-source text-to-speech model — high-quality voice synthesis with multilingual support and voice cloning.

https://github.com/bytedance/megatts3Open Source2mo ago

MLX Audio

Speech library built on Apple's MLX — text-to-speech, speech-to-text, and speech-to-speech with efficient on-device inference on Apple Silicon.

github.com/blaizzy/mlx-audioOpen Source2mo ago

FunASR

An industrial-grade speech-recognition toolkit with 170x-realtime inference, 50+ languages, and speaker diarization.

github.com/modelscope/funasr1mo ago

Supertonic

A lightning-fast, on-device, multilingual text-to-speech engine running via ONNX.

github.com/supertone-inc/supertonic1mo ago

ClawdTalk

ClawdTalk adds voice capabilities to your existing chatbots, allowing users to call and speak with their bots over the phone. It handles speech-to-text and text-to-speech conversion while your bot continues to process text normally.

clawdtalk.comFreemium5mo ago

HyperYapper

Dimillian's app for yapping like a pro — fast, fluid stream-of-consciousness composer with smart organization after the fact.

github.com/dimillian/hyperyapperOpen Source2mo ago

VoxCPM2

A tokenizer-free text-to-speech system that generates high-quality multilingual speech with voice cloning and creative voice design capabilities. Supports 30 languages and can create new voices from text descriptions alone or clone existing voices from audio samples.

github.com/openbmb/voxcpmOpen Source3mo ago

AI Phone Agent

AI-powered phone agent for handling voice calls.

https://github.com/mksglu/ai-phone-agentOpen Source2mo ago

voicebot

rUv's voice-driven AI bot — real-time speech-to-speech agent for hands-free interaction with LLMs.

github.com/ruvnet/voicebotOpen Source2mo ago

Whisper

OpenAI's robust speech recognition model trained on 680k hours of multilingual audio, with strong performance on accents and technical language.

https://github.com/openai/whisperOpen Source2mo ago

Whisper.cpp

High-performance C/C++ port of OpenAI's Whisper. Runs on-device with no Python dependency.

github.com/ggerganov/whisper.cppOpen Source3mo ago