Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root required.
+801this week Created 30 days ago
Tools
Speech-to-text tools that run locally
Open speech models are now good enough for daily dictation, meeting notes and subtitles without sending audio to a cloud service. This collection covers desktop dictation apps you trigger with a shortcut and the engines underneath them.
Apps are the quickest to try; engines matter if you transcribe long recordings or need word-level timestamps and speaker labels. Speed depends heavily on your hardware and the model size you pick.
- Repos tracked
- 46
- New this week
- +4
- added to the list
- Stars gained in 30 days
- +55k
- across 35 ranked repos
- Updated
- Oct 17, 2026
Rising newcomers
11 newcomersCreated in the last 90 days and gaining at least 20 stars this week.
BYOK voice recording companion with ASR transcription, speaker diarization, AI summaries, and local ASR endpoint support.
+324this week Created 73 days ago
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.
+306this week Created 9 days ago
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.
+139this week Created 18 days ago
Real-time captions and translation. 一款开源的实时字幕与翻译软件
+135this week Created 19 days ago
把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio.
+76this week Created 86 days ago
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
+60this week Created 49 days ago
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
+55this week Created 82 days ago
jankeesvw/omarchy-meeting-recorderOpen jankeesvw/omarchy-meeting-recorder on GitHub (opens in new tab)
NewRecord meetings on Omarchy: mic and computer audio as two tracks, transcribed on your own machine, with speakers, chapters and a player.
+41this week Created 22 days ago
Subtitle any video without uploading it. Whisper, translation, styling and burn-in — all local, in the browser, on the desktop, or from the command line.
+36this week Created 37 days ago
Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.
+20this week Created 70 days ago
How this list is ranked
60% momentum, 40% health. Newcomers: created in the last 90 days with ≥ 20 stars this week.
How the score is computed
- Health (0–100) reflects release cadence, recent commit activity and the number of active contributors.
- Momentum (0–100) is stars gained in 30 days ÷ √(stars before), scaled within this collection, so a small project growing fast can outrank a large one.
- Newcomers are listed only in their own block, so a repo never appears twice.
- Members come from matching rules (GitHub topics, keywords in the description and README) plus a short hand-kept include and exclude list. The ranking is recomputed every hour from public GitHub activity.
Ranking
35 reposRanked by momentum, then health
- Rank 1
0xShug0/audio.cppOpen 0xShug0/audio.cpp on GitHub (opens in new tab)
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
+774 stars in 30 days −23% vs previous 30 days Score 94 - Rank 2
debpalash/VoiceStudioOpen debpalash/VoiceStudio on GitHub (opens in new tab)
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
+39.5k stars in 30 days +77% vs previous 30 days Score 92 - Rank 3
cjpais/HandyOpen cjpais/Handy on GitHub (opens in new tab)
A free, open source, and extensible speech-to-text application that works completely offline.
+2.3k stars in 30 days +15% vs previous 30 days Score 91 - Rank 4
stemdeckapp/stemdeckOpen stemdeckapp/stemdeck on GitHub (opens in new tab)
Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative audio workflows through a modern and interactive interface
+397 stars in 30 days −77% vs previous 30 days Score 86 - Rank 5
altic-dev/FluidVoiceOpen altic-dev/FluidVoice on GitHub (opens in new tab)
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM us on X exclusive model access! 😉 - https://x.com/fluidvoiceapp
+693 stars in 30 days −30% vs previous 30 days Score 85 - Rank 6
jamiepine/voiceboxOpen jamiepine/voicebox on GitHub (opens in new tab)
The open-source AI voice studio. Clone, dictate, create.
+3k stars in 30 days −30% vs previous 30 days Score 78 - Rank 7
k2-fsa/sherpa-onnxOpen k2-fsa/sherpa-onnx on GitHub (opens in new tab)
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
+517 stars in 30 days −17% vs previous 30 days Score 76 - Rank 8
Zackriya-Solutions/meetilyOpen Zackriya-Solutions/meetily on GitHub (opens in new tab)
Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows. Understand How to write meeting minutes
+1k stars in 30 days −31% vs previous 30 days Score 72 - Rank 9
chidiwilliams/buzzOpen chidiwilliams/buzz on GitHub (opens in new tab)
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
+539 stars in 30 days −4% vs previous 30 days Score 72 - Rank 10
peteonrails/voxtypeOpen peteonrails/voxtype on GitHub (opens in new tab)
Voice-to-text with push-to-talk for Wayland compositors
+177 stars in 30 days −48% vs previous 30 days Score 71
- Rank 11
tacshi/SoundcoreOpen tacshi/Soundcore on GitHub (opens in new tab)
soundcore Work（安克 AI 录音豆 / D3200）本地管理 App：BLE 配对连接、录音管理、AI 实时转写、Wi-Fi SoftAP 批量导出
+154 stars in 30 days +863% vs previous 30 days Score 68 - Rank 12
tover0314-w/opentypelessOpen tover0314-w/opentypeless on GitHub (opens in new tab)
Open-source AI voice typing for macOS, Windows, and Linux. Press a hotkey, speak naturally, get polished text in any app.
+83 stars in 30 days −7% vs previous 30 days Score 67 - Rank 13
openclaw-easy/ViralMintOpen openclaw-easy/ViralMint on GitHub (opens in new tab)
Open-source video pipeline (clipper, AI video & more) — scout trends, clip long videos, generate captioned shorts, design motion graphics. Local-first, BYOK. AGPL-3.0.
+56 stars in 30 days +75% vs previous 30 days Score 64 - Rank 14
Anil-matcha/AI-Youtube-Shorts-GeneratorOpen Anil-matcha/AI-Youtube-Shorts-Generator on GitHub (opens in new tab)
Open-source alternative to Opus Clip, Vidyo.ai, Klap & SubMagic. Turn long-form YouTube videos into viral 9:16 shorts using LLM highlight detection, Whisper transcription, and auto vertical cropping — free, no watermarks, no per-clip credits.
+419 stars in 30 days +5% vs previous 30 days Score 63 - Rank 15
ggml-org/whisper.cppOpen ggml-org/whisper.cpp on GitHub (opens in new tab)
Port of OpenAI's Whisper model in C/C++
+788 stars in 30 days ±0% vs previous 30 days Score 63 - Rank 16
screenpipe/screenpipeOpen screenpipe/screenpipe on GitHub (opens in new tab)
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
+410 stars in 30 days −26% vs previous 30 days Score 60 - Rank 17
BasedHardware/omiOpen BasedHardware/omi on GitHub (opens in new tab)
AI that sees your screen, listens to your conversations and tells you what to do
+297 stars in 30 days −13% vs previous 30 days Score 60 - Rank 18
goodroot/hyprwhsprOpen goodroot/hyprwhspr on GitHub (opens in new tab)
Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation
+42 stars in 30 days −2% vs previous 30 days Score 58 - Rank 19
mozilla-ai/llamafileOpen mozilla-ai/llamafile on GitHub (opens in new tab)
Distribute and run LLMs with a single file.
+420 stars in 30 days +5% vs previous 30 days Score 56 - Rank 20
openai/whisperOpen openai/whisper on GitHub (opens in new tab)
Robust Speech Recognition via Large-Scale Weak Supervision
+1.6k stars in 30 days −14% vs previous 30 days Score 54 - Rank 21
m-bain/whisperXOpen m-bain/whisperX on GitHub (opens in new tab)
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
+572 stars in 30 days +20% vs previous 30 days Score 51 - Rank 22
NVIDIA-NeMo/SpeechOpen NVIDIA-NeMo/Speech on GitHub (opens in new tab)
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
+141 stars in 30 days −53% vs previous 30 days Score 50 - Rank 23
niedev/RTranslatorOpen niedev/RTranslator on GitHub (opens in new tab)
Open source real-time translation app for Android that runs locally
+134 stars in 30 days +31% vs previous 30 days Score 49 - Rank 24
SYSTRAN/faster-whisperOpen SYSTRAN/faster-whisper on GitHub (opens in new tab)
Faster Whisper transcription with CTranslate2
+503 stars in 30 days −1% vs previous 30 days Score 48 - Rank 25
QuentinFuxa/WhisperLiveKitOpen QuentinFuxa/WhisperLiveKit on GitHub (opens in new tab)
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
+115 stars in 30 days −75% vs previous 30 days Score 47 - Rank 26
mkiol/dsnoteOpen mkiol/dsnote on GitHub (opens in new tab)
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
+40 stars in 30 days −29% vs previous 30 days Score 46 - Rank 27
software-mansion/react-native-executorchOpen software-mansion/react-native-executorch on GitHub (opens in new tab)
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
+28 stars in 30 days −46% vs previous 30 days Score 46 - Rank 28
leon-ai/leonOpen leon-ai/leon on GitHub (opens in new tab)
🧠 Leon is your open-source personal assistant.
+94 stars in 30 days −4% vs previous 30 days Score 43 - Rank 29
collabora/WhisperLiveOpen collabora/WhisperLive on GitHub (opens in new tab)
A nearly-live implementation of OpenAI's Whisper.
+44 stars in 30 days −29% vs previous 30 days Score 39 - Rank 30
argmaxinc/argmax-oss-swiftOpen argmaxinc/argmax-oss-swift on GitHub (opens in new tab)
On-device Speech AI for Apple Silicon
+47 stars in 30 days −6% vs previous 30 days Score 33 - Rank 31
speechbrain/speechbrainOpen speechbrain/speechbrain on GitHub (opens in new tab)
A PyTorch-based Speech Toolkit
+67 stars in 30 days −8% vs previous 30 days Score 32 - Rank 32
team-telnyx/aiOpen team-telnyx/ai on GitHub (opens in new tab)
Official one-stop shop for AI Agents and developers building with Telnyx.
+5 stars in 30 days −44% vs previous 30 days Score 32 - Rank 33
woheller69/whisperIMEOpen woheller69/whisperIME on GitHub (opens in new tab)
Android Input Method Editor (IME) based on Whisper
+11 stars in 30 days −54% vs previous 30 days Score 25 - Rank 34
HeyWillow/willowOpen HeyWillow/willow on GitHub (opens in new tab)
Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative
+23 stars in 30 days +21% vs previous 30 days Score 21 - Rank 35
PaddlePaddle/PaddleXOpen PaddlePaddle/PaddleX on GitHub (opens in new tab)
All-in-One Development Tool based on PaddlePaddle
+18 stars in 30 days −28% vs previous 30 days Score 10
Showing 10 of 35 ranked repos. 11 newcomers are listed separately.