๐Ÿ† #2,110 overall#266 of 301 in Speech Recognition๐Ÿ”ฅ active this week

XimilalaXiang /DeLive

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

$ git clone https://github.com/XimilalaXiang/DeLive.git
GitHub social preview for XimilalaXiang/DeLive
Stars
276
276
Forks
17
17
Language
TypeScript
License
Apache-2.0
Created
Jan 19, 2026
0.7 years old
Last push
Sep 23, 2026
๐Ÿ”ฅ this week

Categories

GitHub topics

More in Speech Recognition

Speech Recognition

xixihhhh/hotclip๐Ÿ”ฅ active

ๅ…่ดนๅผ€ๆบ็š„ AI ๅ‰ช่พ‘ / ็›ดๆ’ญๅˆ‡็‰‡ๅทฅๅ…ท:้•ฟ่ง†้ข‘ใ€็›ดๆ’ญๅ›žๆ”พใ€ๆ’ญๅฎขไธ€้”ฎๅˆ‡ๆˆ็ˆ†ๆฌพ็ซ–ๅฑ็Ÿญ่ง†้ข‘,็›ดๅ‘ๆŠ–้Ÿณ/ๅฟซๆ‰‹/B็ซ™/ๅฐ็บขไนฆ/่ง†้ข‘ๅทโ€”โ€”AI ๆ‰พ้ซ˜ๅ…‰้‡‘ๅฅใ€ๅผนๅน•็ƒญๅบฆ่ฟ›็ˆ†็‚นๅˆคๆ–ญใ€่‡ชๅŠจๅŠ ๅญ—ๅน•ใ€ๆจชๅฑ่ฝฌ็ซ–ๅฑ,ๆœฌๅœฐ่ฟ่กŒๆ— ๆฐดๅฐไธไธŠไผ  | Free open-source Opus Clip alternative, 100% local: AI clips long videos & livestream VODs into viral 9:16 shorts for TikTok & YouTube Shorts. No credits, no watermark, no uploads. Win/macOS/Linux.

TypeScriptAGPL-3.0updated Sep 23, 2026
GitHub โ†—โ˜… 224โ‘‚ 41
Speech Recognition

crosswk/SayIt๐Ÿ”ฅ active

Open-source voice typing for Windows โ€” 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.

TypeScriptAGPL-3.0updated Sep 24, 2026
GitHub โ†—โ˜… 421โ‘‚ 63
Speech Recognition

NsLearning/LangHelper

Striving to create a great Application with full functions of learning languages by ChatGPT, TTS, STT and other awesome AI models, supports talking, speaking assessment, memorizing words with contexts, Listening test, so on.

RustMITupdated Nov 23, 2023
GitHub โ†—โ˜… 348โ‘‚ 23
Speech Recognition

AnubhavChaturvedi-GitHub/jarvis-ai-assistant

Voice-controlled AI desktop assistant in Python. Speech recognition, text to speech, real-time web search, image generation, computer vision and WhatsApp automation, inspired by Iron Man's JARVIS.

PythonGPL-3.0updated Aug 12, 2026
GitHub โ†—โ˜… 344โ‘‚ 68
Speech Recognition

QuintinShaw/openasr๐Ÿ”ฅ active

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 Sep 21, 2026
GitHub โ†—โ˜… 278โ‘‚ 27

Data from GitHub ยท snapshot Sep 24, 2026