Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

232

repo · sayfa 1 / 5

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif speech-to-text

1
flagpupaexplode/offline-whisper-transcriber-windows 16
Offline Whisper Transcriber for Windows. Speech to text in a local-first workspace. Desktop UI reference, sample workflows, and external dow
4/gün ort. +3 son gün 2 commit 1 yazar Go 01 Kas 2026 güncellendi 4 gün önce
audio-to-text batch-transcription local-ai meeting-transcripts offline-transcription podcast-transcription speech-recognition speech-to-text
16
2
floatboatai/OpenMinutes 108
OpenMinutes · 录音笔工作台：MemoTalk S1 录音的导入 · 转录 · AI 归类 · 检索复盘（Floatboat Workbench 开源实现）
13,5/gün ort. +0 son gün 59 commit 1 yazar TypeScript 28 Eki 2026 güncellendi 6 gün önce
ai-classification floatboat react speech-to-text sqlite transcription typescript voice-recorder
108
3
0xCoach/TaoSheng 24
涛声 TaoSheng：用一部安卓手机全天收音 → 转写 → 认人 → AI 整理成待办与记忆。无需硬件、无需账号，数据只在你手机里。
2/gün ort. +0 son gün — commit Kotlin 24 Eki 2026 güncellendi 3 gün önce
ai android jetpack-compose kotlin lifelog llm omi on-device-ai
24
4
vasikmansuri/universal-calling-agent-toolkit 13
Provider-neutral telephony adapters, audio pipeline, email capture, STT and RAG for the AI calling agent you already have. TypeScript + Pyth
1/gün ort. +0 son gün — commit Python 23 Eki 2026 güncellendi 3 gün önce
ai-agents audio-processing calling-agent conversational-ai deepgram llm plivo python
13
5
ishangautam7/Talvio 55
Talk to your computer: dictation into any app, a voice assistant that answers out loud and gets things done, meeting notes, and a phone app
3,9/gün ort. +1 son gün 341 commit 1 yazar Rust 22 Eki 2026 güncellendi 9 gün önce
ai-assistant android dictation llm local-first open-source productivity rust
55
6
third-intelligence/Haas-ASR 36
Inference code for Haas, fast and accurate Japanese speech recognition
2,6/gün ort. +1 son gün — commit Python 22 Eki 2026 güncellendi 6 gün önce
asr japanese speech-recognition speech-to-text
36
7
sebytzr16/on-device-llm 16
Private, offline AI assistant for Android and Windows: run local LLMs (Gemma 4, Qwen, any GGUF) on your phone or PC with llama.cpp, CUDA and
1,1/gün ort. +3 son gün — commit Dart 22 Eki 2026 güncellendi dün
android flutter gemma gguf llama-cpp llm on-device-ai privacy
16
8
modulate-ai/speech-to-text-benchmark 52
Reproducible speech-to-text benchmark: WER, latency and cost for Velma, Deepgram, AssemblyAI, Chirp 3, MAI-Transcribe 2, Moonshine and whisp
3,5/gün ort. -1 son gün 5 commit 3 yazar Python 21 Eki 2026 güncellendi 8 gün önce
asr benchmark speech-recognition speech-to-text transcription velma wer
52
9
SonicloudTech/mouse-mcp 114
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmwar
7,1/gün ort. +0 son gün 9 commit 2 yazar TypeScript 20 Eki 2026 güncellendi 5 gün önce
ai-agents computer-use desktop-automation hardware mcp mcp-server model-context-protocol mouse-control
114
10
C4rohan/Lampline 509
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call
29,9/gün ort. -15 son gün 143 commit 3 yazar Python 19 Eki 2026 güncellendi 3 gün önce
agents-as-code contact-center conversational-ai cx-agent-studio dialogflow-cx ivr llm pipecat
509
11
andrisgauracs/whistle-esp32 213
Whistle speech-to-text running fully on an ESP32-S3: hold a button, say a colour in one of 7 languages, the LED does it. No network.
12,5/gün ort. +2 son gün 2 commit 2 yazar C 19 Eki 2026 güncellendi 15 gün önce
edge-ai esp32 esp32-s3 inmp441 speech-recognition speech-to-text tinyml whistle
213
12
yaya-sy/specspeech 37
Speculative Decoding for fast ASR and TTS inference
2,1/gün ort. +1 son gün — commit Python 18 Eki 2026 güncellendi 10 gün önce
asr speech speech-llm speech-llms speech-recognition speech-synthesis speech-to-text
37
13
Twilightioglorify/talk-type 3
Published: 2026-10-19
0,2/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 17 gün önce
ai-tools csharp dictation dotnet global-hotkey mit-license offline open-source
3
14
FlaxXTT/Typeleast 112
TypeLeast：按一下快捷键说话，本机识别（SenseVoice），用你自己的大模型 API Key 整理成通顺文字，直接写进光标处。macOS + Windows 11。
5,9/gün ort. +17 son gün 284 commit 1 yazar Swift 17 Eki 2026 güncellendi bugün
deepseek dictation llm macos sensevoice sherpa-onnx speech-to-text typeless-alternative
112
15
byteyu2436/tidytalk 13
Tidytalk：Mac 本地语音输入工具。按住说话，松开即可得到整理后的文本。语音识别完全本机运行，可搭配 Ollama 本地大模型润色转写内容，数据不会离开你的电脑。免费开源。| Private on-device voice input for Mac. Hold to s
0,7/gün ort. +0 son gün — commit Swift 16 Eki 2026 güncellendi 8 gün önce
dictation llm macos menu-bar-app ollama speech-recognition speech-to-text swift
13
16
hehehai/AudioSmith 213
Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source.
9,3/gün ort. +15 son gün 839 commit 1 yazar Go 13 Eki 2026 güncellendi 2 gün önce
speaker-diarization speech-synthesis speech-to-text text-to-speech transcription tts voice-cloning voice-design
213
17
zephyr4123/speakmore 189
SpeakMore：口述成文，划词即译。开源、免费的语音输入与翻译工具，支持 Mac 与 Windows：语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务，语音输入亦
8,2/gün ort. +5 son gün 750 commit 3 yazar JavaScript 13 Eki 2026 güncellendi dün
cli dictation electron gemini macos nodejs reverse-engineering speech-to-text
189
18
pyk-boo/ai-interview-helper 14
🎯 Free & open-source AI interview copilot. Real-time answers from voice + screenshots for coding and job interviews. Works with Groq, Claude
0,6/gün ort. +1 son gün — commit JavaScript 12 Eki 2026 güncellendi 8 gün önce
ai-assistant electron groq interview-preparation llm ollama speech-to-text whisper
14
19
ozcancelik/harfiyen 116
Tarayıcıda çalışan Türkçe konuşma tanıma ve altyazı aracı. Otomatik noktalama, canlı transkript ve altyazılı video dışa aktarma. Tamamen yer
4,3/gün ort. -1 son gün 71 commit 2 yazar TypeScript 09 Eki 2026 güncellendi 13 gün önce
local-first onnx onnxruntime-web speech speech-recognition speech-to-text subtitles transcription
116
20
opennookorg/betterwispr 505
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 wit
17,4/gün ort. +2 son gün 232 commit 4 yazar Swift 07 Eki 2026 güncellendi 12 gün önce
apple-silicon dictation local-first macos meeting-notes offline open-source parakeet
505
21
DragonKingIO/Cadenza-voice 24
Local-first voice input for macOS (随言). Hold a shortcut, speak, and the text is typed at your cursor. Recognition runs on your Mac with Sens
0,8/gün ort. +0 son gün — commit Swift 07 Eki 2026 güncellendi 4 gün önce
asr dictation local-first macos menu-bar-app offline open-source privacy
24
22
estebanstifli/OpenDub 18
Local AI video dubbing studio with voice cloning, speech translation, speaker diarization and audio separation. Edit, preview and export dub
0,6/gün ort. +0 son gün — commit C# 07 Eki 2026 güncellendi 26 gün önce
ai-dubbing audio-separation avalonia dotnet ffmpeg indextts llama-cpp local-ai
18
23
vladkens/wavo 17
Local speech-to-text at GPU speed: Parakeet, GigaAM and Whisper in pure Rust, as a library and an ollama-like CLI
0,6/gün ort. +4 son gün — commit Rust 07 Eki 2026 güncellendi dün
apple-silicon asr cli gguf gigaam gpu metal offline
17
24
100yenadmin/fish-audio-hermes 110
Official Fish Audio plugin for Hermes Agent: expressive text-to-speech, speech-to-text, voice library, cloning and voice design.
3,5/gün ort. -2 son gün 32 commit 1 yazar Python 05 Eki 2026 güncellendi 6 gün önce
fish-audio hermes-agent hermes-plugin speech-to-text stt text-to-speech tts voice-cloning
110
25
fotonik-sk/stm32n6-speech-recognition 46
Offline speech-to-text on the STM32N6 microcontroller: free English speech recognition on the NPU, no cloud
1,4/gün ort. +0 son gün — commit C 04 Eki 2026 güncellendi 04 Eki 2026
asr asr-model edge-ai embedded npu offline speech-recognition speech-to-text
46
26
ronitgupta138/Vox-Intel-Engine 43
🎙️ Real-Time Multi-Modal Speech Telemetry & Acoustic DSP Engine (FastAPI, Python 3.11, Autocorrelation Pitch, FFT Spectral Energy & Lexical
1,3/gün ort. +0 son gün — commit Python 04 Eki 2026 güncellendi dün
audio-processing dsp fastapi multimodal-ai nlp presentation-coach python signal-processing
43
27
mallahyari/nemotron-asr-streaming-farsi 70
Streaming Persian (Farsi) speech recognition: fine-tuning NVIDIA Nemotron 3.5 ASR streaming. Data prep, training, evaluation, inference.
2,1/gün ort. +2 son gün 0 commit 0 yazar Python 03 Eki 2026 güncellendi 03 Eki 2026
asr asr-model persian speech-recognition speech-to-text stt
70
28
watzon/sayso 48
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,
1,4/gün ort. +0 son gün — commit Rust 02 Eki 2026 güncellendi bugün
dictation gpui macos parakeet rust speech-to-text voice-typing whisper
48
29
ADITYA-KUMAR-2358/salt-and-story 26
Salt & Story turns voice memos of a relative cooking into clean, printable recipes, while keeping the speaker's own words beside them. Recor
0,8/gün ort. +0 son gün — commit JavaScript 02 Eki 2026 güncellendi 3 gün önce
ai fastapi fastapi-backend open-source open-source-ai open-source-project python python3
26
30
Malmen877/Prata 17
Gratis svensk tal-till-text som körs lokalt på din Mac eller Linux-dator. Transkribera intervjuer och möten offline med KB-Whisper och Klang
0,5/gün ort. +0 son gün — commit Rust 02 Eki 2026 güncellendi 04 Eki 2026
apple-silicon asr kb-whisper kblab linux local-first macos offline
17
31
devladinci/saystack 15
Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.
0,4/gün ort. +0 son gün — commit TypeScript 01 Eki 2026 güncellendi 05 Eki 2026
audio-visualization chat-ui dictation llm openai openai-compatible react react-native
15
32
lokutor-ai/oido önem 53gpt6-luna uyum 46gpt6-luna 130
Oído, ESP32-S3 üzerinde cloud veya NPU olmadan open-vocabulary speech recognition çalıştırmayı hedefleyen C tabanlı bir ASR motorudur.
Neden yükseliyor · Düşük maliyetli bir mikrodenetleyicide open-vocabulary ASR çalıştırma iddiası ve README’de verilen LibriSpeech sonuçları dikkat çekiyor. Repo 1 günlük ve 46 yıldız almış olsa da son 28 gündeki 6 commit’in tek yazardan gelmesi, ilginin henüz bağımsız benimseme veya sürdürülebilir geliştirme kanıtı olmadığını gösteriyor.
3,6/gün ort. +1 son gün 19 commit 3 yazar C 30 Eyl 2026 güncellendi bugün
asr conformer edge-ai embedded esp-idf esp32 esp32-s3 microcontroller
130
33
openmimir/openmimir 13
Talk to all your coding agents. One hands-free, full-duplex voice conversation over Claude Code, Codex and OpenCode. Runs on macOS and Windo
0,4/gün ort. +0 son gün — commit TypeScript 30 Eyl 2026 güncellendi 17 gün önce
coding-agents developer-tools gpt-live hands-free opencode voice ai-agents claude-code
13
34
Digisensus/digisensus-recorder 18
Free, open source call recorder and bot-free AI meeting note taker for Mac: record Zoom, Meet, Teams, FaceTime, WhatsApp and phone calls, ge
0,5/gün ort. +0 son gün — commit Swift 29 Eyl 2026 güncellendi 9 gün önce
ai-note-taker audio-recorder bot-free call-recorder granola-alternative macos mcp-server meeting-notes
18
35
jakemanger/whatmodel 46
Find the best AI models you can run
1,2/gün ort. +1 son gün — commit TypeScript 28 Eyl 2026 güncellendi 2 gün önce
agent ai ai-leaderboard image-generation leaderboard llm llm-agents llm-evaluation
46
36
sunerpy/voltip 87
Push-to-talk voice typing for Windows, macOS, Linux and Android. On-device or cloud speech recognition, AI polish with presets, a dictionary
2,2/gün ort. +1 son gün — commit Rust 27 Eyl 2026 güncellendi dün
android asr cross-platform dictation end-to-end-encryption llm noise-protocol offline
87
37
tlack/babytalk 55
Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for
1,4/gün ort. +0 son gün — commit C 26 Eyl 2026 güncellendi 2 gün önce
asr atomvm edge-ai elixir erlang esp-idf esp32 esp32-p4
55
38
Sallyn0225/eidolon-sc 393
和《偶像大师闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon）
9,6/gün ort. +7 son gün 1.098 commit 1 yazar Python 25 Eyl 2026 güncellendi dün
ai-companion character-ai docker-compose fastapi idolmaster llm nextjs pipecat
393
39
AGIHunt/blurt 271
The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your o
6,6/gün ort. +20 son gün 785 commit 1 yazar Swift 25 Eyl 2026 güncellendi 3 gün önce
agent-skills claude-code codex screen-recording speech-recognition vibe-coding ai-agents feedback
271
40
olerast67/voice-teleprompter-android 78
Suflyor (Суфлёр): free voice-following teleprompter app for Android. Scrolls as you speak, floats over Instagram, TikTok and the camera. Spe
1,9/gün ort. +3 son gün — commit Kotlin 25 Eyl 2026 güncellendi dün
android android-app content-creation foss instagram-reels jetpack-compose kotlin offline
78
41
B0yko/tern 214
Local AI search for podcast and video archives on Apple Silicon: Whisper speech, Apple Vision OCR and SigLIP-2 visual search fused into one
5,1/gün ort. +0 son gün 1 commit 1 yazar Python 24 Eyl 2026 güncellendi 10 gün önce
apple-silicon apple-vision chromadb fastapi fcpxml ffmpeg local-first macos
214
42
SomehowLiving/Voxie 17
Voice agents that speak your caller's language: listening, turn-taking, barge-in and the voice, in 29 languages. Open source.
0,4/gün ort. +0 son gün — commit Go 24 Eyl 2026 güncellendi 9 gün önce
ai-agents go multilingual python realtime speech-to-text text-to-speech typescript
17
43
sennett-lau/oratype 13
OraType (formerly Typelite). Just say it. Free, open-source voice typing for macOS: speak in any app and get clean text. Runs on your comput
0,3/gün ort. +0 son gün — commit Rust 24 Eyl 2026 güncellendi dün
ai dictation llama-cpp macos open-source speech-to-text tauri translation
13
44
GeiserX/akou 19
The open-source alternative to Granola. Records your calls on a Mac, transcribes them on your own machine, lets your own AI agent in the ter
0,4/gün ort. +2 son gün — commit TypeScript 23 Eyl 2026 güncellendi 2 gün önce
call-recorder call-transcription claude-code desktop-app electrobun granola-alternative live-transcription local-first
19
45
resonand-app/resonand 24
A self-hosted archive for the recordings that matter 🎧🔒
0,5/gün ort. +0 son gün — commit TypeScript 22 Eyl 2026 güncellendi 2 gün önce
archive audio docker self-hosted speech-to-text transcription whisper
24
46
binders-io/app 25
Binders for macOS: local-first dictation, meeting notes and memory, with an MCP server for your AI tools. Private by design, free, open sour
0,6/gün ort. +0 son gün — commit Swift 21 Eyl 2026 güncellendi 3 gün önce
apple-silicon dictation knowledge-base local-ai local-first macos mcp mcp-server
25
47
equalang/equalang-mcp 22
MCP server for Equalang: translate PDF, DOCX, PPTX, XLSX, EPUB, subtitles, pictures, audio and video with the layout kept; transcribe record
0,5/gün ort. +0 son gün — commit TypeScript 19 Eyl 2026 güncellendi 2 gün önce
claude-code codex cursor document-translation image-translation mcp mcp-server model-context-protocol
22
48
splexuan/video-transcript-workbench 13
本地视频文案提取与校对工具：把视频链接或本地音视频转成可编辑、可导出的文字稿
0,3/gün ort. +0 son gün — commit Python 19 Eyl 2026 güncellendi 05 Eki 2026
bilibili douyin fastapi ffmpeg python react sensevoice speech-to-text
13
49
mynameisjinhohong/interview-studio 25
Local Korean technical interview practice studio powered by Codex, Claude, and Gemini CLIs
0,5/gün ort. +0 son gün — commit TypeScript 17 Eyl 2026 güncellendi 24 Eyl 2026
claude codex electron gemini interview-practice speech-to-text typescript
25
50
nirbhay41120003/EchoMind önem 39gpt6-luna uyum 55gpt6-luna 27
EchoMemory, konuşmaları cihazda yazıya döküp aranabilir belleğe kaydeden ve bu kayıtlar hakkında yerel bir RAG chatbot ile soru sormayı sağlayan bir uygulamadır.
Neden yükseliyor · 11 günde 68 yıldız ve son 28 günde 16 commit ile erken ilgi ve geliştirme hareketliliği var; ancak yalnızca 2 farklı yazar görülüyor. Yerel AI, gizlilik ve konuşma belleğini tek bir kullanıma hazır uygulamada birleştirmesi ilgi çekici olabilir; yıldız sayısı benimseme veya kalite kanıtı değil.
0,5/gün ort. -3 son gün — commit Python 16 Eyl 2026 güncellendi 17 Eyl 2026
accessibility hearing-assistance llama-cpp llama-cpp-python local-llm on-device-ai open-source privacy
27