transcription repositories
Trending repositories tagged transcription, ranked by trending score. Updated daily.
-
1
debpalash/VoiceStudio
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
GitHub · Python · 116,351 stars · 12,948 forks · +1,693 stars in 24 hours · Trending score 6.10
-
2
FrigadeHQ/yogurt
Private AI meeting notes that stay on your computer. No meeting bot. Free and open source for Mac, Windows and Linux. An alternative to Granola, Otter and Fireflies.
GitHub · TypeScript · 2,935 stars · 247 forks · +248 stars in 24 hours · Trending score 4.77
-
3
HUANGCHIHHUNGLeo/claude-real-video
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
GitHub · Python · 2,332 stars · 208 forks · +122 stars in 24 hours · Trending score 3.58
-
4
tmoroney/auto-subs
On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.
GitHub · TypeScript · 4,602 stars · 333 forks · +115 stars in 24 hours · Trending score 3.50
-
5
wassgha/rescript
🎬 Open source, transcript-based video/audio editor that lives in the browser.
GitHub · TypeScript · 1,128 stars · 145 forks · +88 stars in 24 hours · Trending score 3.29
-
6
open-subs/opensubs
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.
GitHub · TypeScript · 182 stars · 11 forks · +62 stars in 24 hours · Trending score 3.03
-
7
Jamailar/Beav
小红书 AI 运营工作台|小红书采集、评论区下载、素材库、选题、AI写作、小红书全域解决方案,开箱即用,一键安装,小红书AI工作台,自媒体素材库,AI写作+图片自动编排,小红书版OpenClaw、自媒体资产底座+AI工作台,支持小红书图文+小红书评论区下载、小红书AI创作工具、自媒体版WorkBuddy、抖音、小红书爬虫数据采集
GitHub · Rust · 2,484 stars · 313 forks · +23 stars in 24 hours · Trending score 2.80
-
8
kaixxx/noScribe
Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)
GitHub · Python · 2,261 stars · 373 forks · +46 stars in 24 hours · Trending score 2.77
-
9
veedstudio/open-edit
Open-source, agent-driven editing pipeline: create subtitles, motion graphics, slides, edit and render videos.
GitHub · TypeScript · 1,849 stars · 121 forks · +66 stars in 24 hours · Trending score 2.76
-
10
pattern-ai-labs/agentcall
AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)
GitHub · Python · 208 stars · 28 forks · +39 stars in 24 hours · Trending score 2.74
-
11
modelscope/FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
GitHub · Python · 21,096 stars · 2,142 forks · +19 stars in 24 hours · Trending score 2.71
-
12
Vexa-ai/vexa
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
GitHub · Python · 3,002 stars · 557 forks · +34 stars in 24 hours · Trending score 2.71
-
13
iskandaryv/meetingly-ai
Open-source AI interview assistant and meeting copilot: live answers during Zoom, Google Meet and Teams calls, on-device transcription, hidden from screen sharing. Free Cluely, Interview Coder and Final Round AI alternative for Windows, macOS, Linux.
GitHub · TypeScript · 670 stars · 35 forks · +39 stars in 24 hours · Trending score 2.67
-
14
gsamat/amanu
Records and transcribes online meetings. Automatically
GitHub · Swift · 254 stars · 48 forks · +24 stars in 24 hours · Trending score 2.50
-
15
naxhq/NexQ
Open-source, local-first AI meeting assistant & real-time interview copilot for Windows and macOS — live transcription, instant AI answers, invisible to screen share.
GitHub · TypeScript · 146 stars · 40 forks · +23 stars in 24 hours · Trending score 2.47
-
16
dimastatz/whisper-flow
Whisper-Flow is a framework designed to enable real-time transcription of audio content using OpenAI’s Whisper model. Rather than processing entire files after upload (“batch mode”), Whisper-Flow accepts a continuous stream of audio chunks and produces incremental transcripts immediately.
GitHub · Python · 1,021 stars · 144 forks · +25 stars in 24 hours · Trending score 2.46
-
17
nyrahealth/CrisperWhisper
Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.
GitHub · Python · 1,499 stars · 98 forks · +24 stars in 24 hours · Trending score 2.34
-
18
tanpreetjolly/browser-whisper
In-browser Whisper speech-to-text with WebGPU (WASM fallback). Transcribe audio & video locally, no server.
GitHub · TypeScript · 236 stars · 15 forks · +28 stars in 24 hours · Trending score 2.30
-
19
Serkali-sudo/auto-subtitle-generator
An Android app that automatically generates subtitles for videos locally using whisper or vosk
GitHub · C · 98 stars · 19 forks · +21 stars in 24 hours · Trending score 2.23
-
20
BasedHardware/omi
AI that sees your screen, listens to your conversations and tells you what to do
GitHub · Python · 14,009 stars · 2,711 forks · +9 stars in 24 hours · Trending score 2.20
-
21
kouhxp/yapsnap
Transcribe any video URL or audio file into plaintext. No GPU. No cloud. One command.
GitHub · Python · 383 stars · 16 forks · +20 stars in 24 hours · Trending score 2.14
-
22
whispaste/whispaste
Press a hotkey, speak, and your words appear at the cursor. Free, open-source voice input for Windows, macOS and Linux with on-device speech recognition (Whisper, Parakeet); cloud providers optional.
GitHub · Dart · 86 stars · 7 forks · +7 stars in 24 hours · Trending score 2.07
-
23
snapotter-hq/SnapOtter
Free, open-source file toolkit for PDFs, images, video and audio. Compress, convert, OCR, remove backgrounds and transcribe on your own server with one Docker command. 200+ tools, local AI, REST API. An alternative to iLovePDF, TinyWow CloudConvert and remove.bg.
GitHub · TypeScript · 3,004 stars · 190 forks · +8 stars in 24 hours · Trending score 2.02
-
24
QuintinShaw/openasr
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.
GitHub · Rust · 306 stars · 36 forks · +15 stars in 24 hours · Trending score 1.96