🏆 #2,488 overall#310 of 795 in Speech Recognition

crosswk /SayIt

Open-source voice typing for Windows and macOS — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text lands at your cursor. Local models, your own API keys, or a self-hosted backend.

$ git clone https://github.com/crosswk/SayIt.git
GitHub social preview for crosswk/SayIt
Stars
492
492
This week
+13 ★
+52 this month
Forks
66
66
Language
TypeScript
License
AGPL-3.0
Created
May 9, 2026
0.5 years old
Last push
Nov 9, 2026

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 440▲ +52★ 492

Categories

GitHub topics

More in Speech Recognition

Speech Recognition

anomalyco/hex🔥 active

▲ +1.3K ★ this week

Local voice dictation for mac, windows and linux

RustMITupdated Nov 16, 2026
GitHub ↗★ 7.1K⑂ 456
Speech Recognition

hehehai/VoxtMini🔥 active

Voice input for macOS on local models: transcribe, translate and rewrite in any app. The successor of Voxt.

GoApache-2.0updated Nov 16, 2026
GitHub ↗★ 900⑂ 68
Speech Recognition

moona3k/macparakeet

Fast, private, local-first voice app for Apple Silicon Macs — dictation, file/media transcription, meeting recording, Transforms, and a public automation CLI. Free and open-source.

SwiftOtherupdated Nov 9, 2026
GitHub ↗★ 789⑂ 96
Speech Recognition

opennookorg/betterwispr🔥 active

▲ +23 ★ this week

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.

SwiftApache-2.0updated Nov 14, 2026
GitHub ↗★ 540⑂ 55
Speech Recognition

nyosegawa/speech.cpp🔥 active

▲ +83 ★ this week

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.

C++MITupdated Nov 15, 2026
GitHub ↗★ 458⑂ 31
Speech Recognition

QuintinShaw/openasr

▲ +5 ★ this week

Local-first speech-to-text: no cloud, no telemetry, fail-closed by design. One CLI, seven model families, signed model catalog, OpenAI-compatible local API.

RustApache-2.0updated Oct 30, 2026
GitHub ↗★ 303⑂ 34

Data from GitHub · snapshot Nov 16, 2026