1.cjpais / Handy
A free, open source, and extensible speech-to-text application that works completely offline.
- speech-to-text
- tauri-v2
- accessibility
- cross-platform
+4,664 stars
from 32,876 · score 8.45
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
18 repositories by Attention Score · Oct 6, 2026 – Nov 4, 2026 (UTC)
2.jamiepine / voicebox
The open-source AI voice studio. Clone, dictate, create.
+3,111 stars
from 56,312 · score 8.04
3.openai / whisper
Robust Speech Recognition via Large-Scale Weak Supervision
+2,089 stars
from 109,874 · score 7.64
4.Zackriya-Solutions / meetily
Privacy-first AI meeting note taker for Windows and macOS. Free, open source (MIT). On-device Whisper/Parakeet transcription and speaker diarization, no meeting bot. Open-source alternative to Granola, Otter and Fireflies. https://meetily.ai
+1,073 stars
from 31,375 · score 6.98
5.ggml-org / whisper.cpp
Port of OpenAI's Whisper model in C/C++
+844 stars
from 54,086 · score 6.74
6.HanyuanWang / LiveStream-Agent-Studio
TranslatedA Windows local AI Agent Studio for Douyin live-streaming e-commerce, connecting streamer discovery, live stream insights, live stream review, and short-video content directing into one unified intelligent workflow.
- ai-agent
- douyin
- livestream
- speech-to-text
+835 stars
from 1,096 · score 6.73
7.SYSTRAN / faster-whisper
Faster Whisper transcription with CTranslate2
- deep-learning
- inference
- quantization
- speech-recognition
- speech-to-text
- transformer
- +2 more
+794 stars
from 25,689 · score 6.68
+725 stars
from 54,555 · score 6.59
9.chidiwilliams / buzz
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
+632 stars
from 21,783 · score 6.45
10.modelscope / FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
- pytorch
- speech-recognition
- paraformer
- punctuation
- speaker-diarization
- voice-activity-detection
- +14 more
+365 stars
from 20,573 · score 5.90
11.BasedHardware / omi
AI that sees your screen, listens to your conversations and tells you what to do
+273 stars
from 13,619 · score 5.61
12.wenxuanzhang1209-cyber / meetdo
TranslatedMeetDo — open-source Meeting-to-Action AI by 筑听 (Zhuting, "build listen") · JKinco Listen. Self-hosted live meetings, local ASR/LLM, structured minutes, DOCX/PDF.
- docker
- fastapi
- funasr
- local-first
- local-llm
- meeting-minutes
- +14 more
+176 stars
from 102 · score 5.18
13.Starmel / OpenSuperWhisper
macOS dictation app
+126 stars
from 2,994 · score 4.84
14.goodroot / hyprwhspr
Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation
- archlinux
- dictation
- hyprland
- omarchy
- speech-to-text
- waybar
- +14 more
+41 stars
from 1,230 · score 3.74
15.woheller69 / whisperIME
Android Input Method Editor (IME) based on Whisper
- android
- on-device-ai
- speech-recognition
- transcription
- translation
- whisper
- +1 more
+15 stars
from 641 · score 2.77
16.sammargolis / OpenScribe
OpenScribe is an open-source AI scribe that records patient encounters and generates structured clinical notes automatically. You keep full control over data, workflows, and patient privacy with no vendor lock-in.
+13 stars
from 213 · score 2.64
+3 stars
from 6,817 · score 1.39
18.vimalk78 / dictate
Talk to Claude Code instead of typing — on Linux. Local voice-to-text using Whisper, no cloud, no API keys.
+2 stars
from 22 · score 1.10