Açık kaynak radarı

Havuz

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

repo · sayfa 1 / 2

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
floatboatai/OpenMinutes 106
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）
10,6/gün ort. -1 son gün 59 commit 1 yazar TypeScript 28 Eki 2026 güncellendi 8 gün önce
ai-classification floatboat memotalk react speech-to-text sqlite transcription typescript
106
2
SonicloudTech/mouse-mcp 119
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmwar
6,6/gün ort. +5 son gün 9 commit 2 yazar TypeScript 20 Eki 2026 güncellendi 7 gün önce
ai-agents computer-use desktop-automation hardware hid mcp mcp-server model-context-protocol
119
3
C4rohan/Lampline 462
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
24,3/gün ort. +0 son gün 143 commit 3 yazar Python 19 Eki 2026 güncellendi 5 gün önce
agents-as-code contact-center conversational-ai cx-agent-studio dialogflow-cx ivr llm pipecat
462
4
andrisgauracs/whistle-esp32 214
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.
11,3/gün ort. +0 son gün 2 commit 2 yazar C 19 Eki 2026 güncellendi 17 gün önce
edge-ai esp32 esp32-s3 inmp441 speech-recognition speech-to-text tinyml whistle
214
5
FlaxXTT/Typeleast 120
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。
5,7/gün ort. +0 son gün 296 commit 1 yazar Swift 17 Eki 2026 güncellendi dün
deepseek dictation llm macos sensevoice sherpa-onnx speech-to-text typeless-alternative
120
6
hehehai/AudioSmith 226
Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source.
9/gün ort. +2 son gün 840 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
226
7
zephyr4123/speakmore 192
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
7,7/gün ort. +2 son gün 750 commit 3 yazar JavaScript 13 Eki 2026 güncellendi 3 gün önce
asr cli deepseek dictation electron gemini llm macos
192
8
ozcancelik/harfiyen 116
Tarayıcıda çalışan Türkçe konuşma tanıma ve altyazı aracı. Otomatik noktalama, canlı transkript ve altyazılı video dışa aktarma. Tamamen yer
4/gün ort. +0 son gün — commit TypeScript 09 Eki 2026 güncellendi 15 gün önce
local-first onnx onnxruntime-web speech speech-recognition speech-to-text subtitles transcription
116
9
opennookorg/betterwispr 514
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
16,6/gün ort. +2 son gün 208 commit 9 yazar Swift 07 Eki 2026 güncellendi bugün
apple-silicon dictation local-first macos meeting-notes offline open-source parakeet
514
10
lokutor-ai/oido önem 53gpt6-luna uyum 46gpt6-luna 131
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.
3,4/gün ort. +1 son gün — commit C 30 Eyl 2026 güncellendi 2 gün önce
asr conformer edge-ai embedded esp-idf esp32 esp32-s3 int4
131
11
Sallyn0225/eidolon-sc 402
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）
9,3/gün ort. +6 son gün 989 commit 1 yazar Python 25 Eyl 2026 güncellendi 3 gün önce
ai-companion character-ai docker-compose fastapi idolmaster llm nextjs pipecat
402
12
AGIHunt/blurt 287
The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your o
6,7/gün ort. +5 son gün 791 commit 1 yazar Swift 25 Eyl 2026 güncellendi dün
agent-skills ai-agents claude-code codex dictation feedback macos ocr
287
13
B0yko/tern 190
Local AI search for podcast and video archives on Apple Silicon: Whisper speech, Apple Vision OCR and SigLIP-2 visual search fused into one
4,3/gün ort. -20 son gün 3 commit 1 yazar Python 24 Eyl 2026 güncellendi bugün
apple-silicon apple-vision chromadb fastapi fcpxml ffmpeg local-first macos
190
14
software-mansion/runntime 119
High-performance neural networks engine for web, built on top of TypeGPU
2,2/gün ort. +0 son gün 49 commit 3 yazar TypeScript 14 Eyl 2026 güncellendi dün
ai computer-vision edge llm ml nlp on-device runtime
119
15
zhuzhangxue/wechat-chat-export 127
Windows 微信 4.1.12+ 聊天记录本地导出工具：TXT / Markdown / JSON，支持图片、文件、语音、视频、本地语音转文字和聊天预览，面向 GPT、Claude、Gemini 等 LLM。 | Local-first WeChat chat exporte
1,8/gün ort. +1 son gün 2 commit 1 yazar Python 29 Ağu 2026 güncellendi 25 gün önce
chat-export chat-history chatgpt claude gemini grok llm local-first
127
16
fermionresearch/phonon 331
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
4,7/gün ort. +0 son gün 5 commit 1 yazar Python 28 Ağu 2026 güncellendi 10 gün önce
asr cuda docker low-bit mlx pytorch quantization speech-recognition
331
17
wenxuanzhang1209-cyber/meetdo 308
MeetDo — open-source Meeting-to-Action AI by 筑听 · JKinco Listen. Self-hosted live meetings, local ASR/LLM, structured minutes, DOCX/PDF.
3,9/gün ort. +0 son gün 5 commit 1 yazar Python 21 Ağu 2026 güncellendi bugün
docker fastapi funasr local-first local-llm meeting-minutes offline-first ollama
308
18
moznoazachem/giga-pisar 117
Гига Писарь: бесплатная локальная русская диктовка для macOS на GigaAM v3. Зажал правый ⌘, сказал, отпустил. Giga Pisar: offline Russian dic
1,4/gün ort. +0 son gün 33 commit 2 yazar Swift 18 Ağu 2026 güncellendi dün
dictation gigaam llama-cpp macos onnx russian speech-recognition speech-to-text
117
19
Fishsb/dsh-voice-prompt-enhancer 123
DeepSeek-Harness (DSH) 插件：✨ 提示词一键增强（5 模式·模型链·记忆链）+ 💬 语音输入增强（热键·说完自动停·口水词清理·语音纠错）
1,4/gün ort. +1 son gün 176 commit 3 yazar JavaScript 13 Ağu 2026 güncellendi bugün
ai-plugin deepseek deepseek-harness dsh dsh-plugin prompt-engineering prompt-enhancement speech-to-text
123
20
allmodels-io/hermes-speech 196
Hermes Agent TTS and STT plugin for AllModels speech models and voices.
2,3/gün ort. -3 son gün 0 commit 0 yazar Python 12 Ağu 2026 güncellendi 28 Eyl 2026
allmodels cartesia elevenlabs fish-audio hermes-agent hermes-plugin hermes-skill openai-compatible
196
21
yuxino-labs/koma 299
Self-hosted AI video analysis: summaries, chapters, keyframes, transcripts and SRT / JSON export. AI 视频总结、字幕提取与结构化分析。
3,3/gün ort. +0 son gün 9 commit 1 yazar TypeScript 08 Ağu 2026 güncellendi 3 gün önce
computer-vision ffmpeg keyframe-extraction self-hosted speech-to-text structured-data subtitles transcription
299
22
tornikegomareli/Talkify 587
Lightning-fast, free, local first voice dictation for macOS with on-device transcription
6,2/gün ort. +0 son gün 10 commit 1 yazar Swift 05 Ağu 2026 güncellendi 21 gün önce
appkit apple-silicon dictation macos menubar-app metal notch speech-recognition
587
23
HuangYincan/VideoNote-MCP 103
VideoNote：将视频转成文字或笔记。理解画面/弹幕/评论；支持本地音视频或主流平台；工具解耦；多格式导出。
1/gün ort. +1 son gün 34 commit 1 yazar Python 31 Tem 2026 güncellendi 17 gün önce
ai-notes bilibili claude-code douyin mcp note-taking python skills
103
24
yusufipk/dikte 210
Voice-to-text dictation app.
2/gün ort. +2 son gün 30 commit 3 yazar Python 25 Tem 2026 güncellendi 9 gün önce
linux open-source speech-to-text transcribe transcription
210
25
FrigadeHQ/yap 467
Free, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud/no API keys/no account.
4,4/gün ort. +1 son gün 4 commit 1 yazar Swift 23 Tem 2026 güncellendi 3 gün önce
accessibility apple-speech dictation macos macos-app menubar offline on-device
467
26
yuxino/Mimi 832
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.
7,7/gün ort. +2 son gün 241 commit 2 yazar Rust 22 Tem 2026 güncellendi dün
macos subtitles tauri audio-capture live-captions speech-recognition windows desktop-app
832
27
anomalyco/hex 5.562
Local voice dictation for mac, windows and linux
49,2/gün ort. +201 son gün 1.299 commit 4 yazar Rust 17 Tem 2026 güncellendi bugün
dictation linux local-first macos rust speech-recognition speech-to-text voice-control
5.562
28
Ali-hey-0/audio-ai-field-guide 144
A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transf
1,3/gün ort. +0 son gün 0 commit 0 yazar 16 Tem 2026 güncellendi 16 Tem 2026
asr audio-processing deep-learning huggingface meachine-learning speech-recognition speech-to-text transformers
144
29
kigner/audio.cpp-webui 419
audio.cpp with a full-task WebUI - pure C++ audio-model inference engine powered by ggml. TTS, ASR/STT, VAD, voice conversion, speaker diari
3,6/gün ort. +0 son gün 268 commit 18 yazar C++ 12 Tem 2026 güncellendi 2 gün önce
asr audio cpp ggml inference-engine music-generation speaker-diarization speech-recognition
419
30
chayapats/oliv 111
Thai + English voice typing for Mac. Offline speech-to-text that types Thai-spoken tech words in English. Push-to-talk dictation on Apple Si
0,9/gün ort. -1 son gün — commit Swift 11 Tem 2026 güncellendi 3 gün önce
apple-silicon dictation local-ai macos mlx offline on-device-ai privacy
111
31
jaromiru/diktafon 288
Diktafon is a private, open-source voice memo app that transcribes and summarizes your recordings entirely on your device — organized like c
2,4/gün ort. +3 son gün 0 commit 0 yazar C++ 09 Tem 2026 güncellendi 30 Tem 2026
android audio-recorder cassette flutter ios llm offline-first open-source
288
32
AudarAI/Audar-ASR-V1 502
Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, ben
4/gün ort. +0 son gün 0 commit 0 yazar Python 06 Tem 2026 güncellendi 22 Ağu 2026
arabic arabic-nlp asr dialectal-arabic gguf huggingface llama-cpp speech-recognition
502
33
MachHongHai/HaizFlow 228
Free Windows desktop app for AI video translation, subtitles and dubbing, with local CPU/GPU models, voice cloning, batch processing and vid
1,8/gün ort. +0 son gün — commit Python 06 Tem 2026 güncellendi 4 gün önce
batch-processing ffmpeg gemini local-ai pyside6 python speaker-diarization speech-to-text
228
34
oxbshw/watch-skill 558
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence
4,5/gün ort. +3 son gün 0 commit 0 yazar Python 05 Tem 2026 güncellendi 12 gün önce
agent-observability agent-skills agentic-ai ai-agents audio-understanding computer-vision deepseek deepseek-harness
558
35
xinkyle/Voconly 153
本地优先 AI 语音输入工具 | Local-first AI voice typing tool. 支持 Whisper/SenseVoice/Parakeet/Qwen asr，离线可用，LLM 智能润色. Open-source speech-to-text with LL
1,2/gün ort. +0 son gün — commit C++ 03 Tem 2026 güncellendi dün
asr llm local-ai offline offline-first parakeet parakeet-model qwen3-asr
153
36
KIRVO-REPORTING/video-to-notes 113
Local-first video-to-notes CLI for YouTube/Bilibili transcripts, Whisper fallback, timestamped AI summaries, and Notion/Obsidian export.
0,9/gün ort. +0 son gün — commit Python 03 Tem 2026 güncellendi 5 gün önce
ai-notes ai-summary bilibili cli codex-skill knowledge-base local-first local-whisper
113
37
0xShug0/audio.cpp önem 68gpt6-luna uyum 83gpt6-luna 4.088
audio.cpp, ggml tabanlı ortak bir C++ runtime üzerinden farklı ses modellerinde yerel inference çalıştırmayı sağlayan bir framework’tür.
Neden yükseliyor · 96 günlük yaşına rağmen 3067 yıldızın yanı sıra son 28 günde 272 commit ve 18 farklı yazar görünüyor; bu, README’deki geniş model desteğinin yanında kayda değer bir geliştirme hareketliliğine işaret ediyor. README performans iyileştirmeleri ve yeni model desteği bildiriyor, ancak bu kıyasların bağımsız doğrulaması verilen bilgilerden anlaşılamıyor.
29,8/gün ort. +31 son gün 326 commit 20 yazar C++ 23 Haz 2026 güncellendi bugün
ai amd-gpu apple-silicon asr audio cpp edge-ai ggml
4.088
38
gojargo/jargo 109
Conversational-AI framework for Go.
0,8/gün ort. +1 son gün — commit Go 18 Haz 2026 güncellendi dün
ai-agents audio conversational-ai go golang llm pion realtime
109
39
AbhishekBarali/SpeakoFlow 390
Free, open-source offline voice dictation for Windows, macOS, and Linux. A Wispr Flow alternative with an AI assistant that can read your sc
2,7/gün ort. +0 son gün 154 commit 4 yazar Rust 17 Haz 2026 güncellendi 7 gün önce
ai-assistant cross-platform dictation local-first offline-speech-recognition privacy-focused rust speech-to-text
390
40
techjarves/Portable-Local-Studio 1.946
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text
12,5/gün ort. +21 son gün 52 commit 5 yazar JavaScript 04 Haz 2026 güncellendi 2 gün önce
image-generation speech-to-text text-generation text-to-speech
1.946
41
0xzr/freellmpool 146
Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.
0,9/gün ort. +0 son gün — commit Python 03 Haz 2026 güncellendi dün
anthropic claude codex cursor failover free-llm free-llm-api gemini
146
42
ariso-ai/oats 103
The free, open-source meeting-notes app for your Mac — offline transcription and AI notes, free in the cloud or 100% on-device.
0,6/gün ort. +0 son gün — commit Rust 23 May 2026 güncellendi 2 gün önce
ai-notes apple-silicon local-first macos meeting-notes menubar-app mlx on-device
103
43
cmagnussen/blitztext-app 265
Local-first dictation for macOS. Speak, text, done. Parakeet or Whisper on your Mac, writing modes with Apple Intelligence. Free, MIT.
1,6/gün ort. +1 son gün 15 commit 3 yazar Swift 22 May 2026 güncellendi dün
macos menubar-app speech-to-text swift whisperkit apple-intelligence dictation local-first
265
44
kouhxp/yapsnap 428
Transcribe any video URL or audio file into plaintext. No GPU. No cloud. One command.
2,5/gün ort. -110 son gün 0 commit 0 yazar Python 20 May 2026 güncellendi 15 Eyl 2026
ai-tools asr cpu diarization speech-recognition speech-to-text subtitles transcription
428
45
crosswk/SayIt 474
Open-source voice typing for Windows and macOS — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text land
2,6/gün ort. +3 son gün 33 commit 2 yazar TypeScript 09 May 2026 güncellendi 4 gün önce
asr qwen3-asr self-hosted speech-recognition speech-to-text tauri voice-input voice-typing
474
46
hwdsl2/self-hosted-ai-stack 177
Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP too
1/gün ort. +3 son gün — commit Shell 05 May 2026 güncellendi 5 gün önce
ai ai-stack docker docker-compose embeddings linux llm local-ai
177
47
Kaitzz/MilkyAi-bilibili 125
MilkyAi at bilibili🥛| Video-to-Notes Email Service with RAG Customer Support & 38K Followers/Users on Bilibili | Python, PostgreSQL, RAG, A
0,7/gün ort. +0 son gün — commit Python 04 May 2026 güncellendi 04 Eki 2026
social-media llm asyncio python asr aws-ses bilibili postgresql
125
48
AhmadHassan-BTed/B 5.206
An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active
27,5/gün ort. +0 son gün 0 commit 0 yazar Python 02 May 2026 güncellendi 07 Tem 2026
ai ai-agent ai-companion artificial-intelligence autonomous-agent computer-vision desktop-assistant llm
5.206
49
artcc/freelingo 245
Open-source, self-hosted AI language learning platform with local or cloud LLMs, CEFR study plans, an AI tutor, voice conversations, flashca
1,3/gün ort. +2 son gün 102 commit 1 yazar JavaScript 30 Nis 2026 güncellendi dün
nextjs python self-hosted ai-tutor cefr docker-compose edtech fastapi
245
50
coval-ai/benchmarks 105
Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.
0,5/gün ort. +0 son gün — commit Python 29 Nis 2026 güncellendi bugün
ai ai-agents speech-to-text text-to-speech voice-ai agent-evaluation ai-evals evals
105