dengyao1

dengyao1 / EchoPass

Public

会议纪要总结+实时转录+说话人确认+AI实时对话+语音唤醒

18
0
100% credibility
Found Apr 25, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

EchoPass is a browser-based real-time meeting voice assistant that transcribes discussions, identifies speakers, generates AI summaries and chapters, responds to wake words, and exports notes.

How It Works

1
🔍 Discover EchoPass

You hear about this friendly meeting helper that listens to conversations and turns them into clear notes with who said what.

2
💻 Get it ready on your computer

Download and set it up quickly on your Mac, Windows, or server following easy pictures and steps.

3
🔌 Link voice and smart helpers

Connect it to speech services and AI thinkers by sharing your simple access details securely.

4
👥 Teach it your team's voices

Record a quick voice sample for each person so it can spot who's talking during meetings.

5
🎤 Record your meeting live

Open it in your web browser, start recording, and see words appear in real-time with speaker names.

6
🗣️ Chat with the assistant anytime

Say a wake phrase like 'Hey Echo' to ask quick questions about the discussion or get insights on the spot.

📦 Grab your perfect meeting notes

Generate summaries, chapters, and action items, then download a tidy package to share and review forever.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 18 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is EchoPass?

EchoPass is a Python-based web app that turns your meetings into structured notes with real-time transcription, speaker identification, AI-generated summaries, and a voice-activated assistant. Point your browser at it, enroll speakers via mic clips, hit record, and get labeled transcripts, chapter breakdowns, and exportable ZIPs with audio, text, and Markdown reports. It solves the drudgery of manual notetaking by handling diarization, wake-word queries like "小云小云," and contextual AI replies via cloud ASR and TTS.

Why is it gaining traction?

It packs end-to-end voice workflow—transcription via Volcengine, local speaker models, LLM summaries with rule-based fallbacks—into a single deployable package with Docker and cross-platform scripts. Developers dig the zero-boilerplate setup: drop API keys in YAML, run a script, access via HTTPS with auto-generated certs. The assistant pulls recent context for smart replies, and exports bundle everything without post-processing.

Who should use this?

Remote Chinese-speaking teams recapping sales calls or standups, where quick speaker-labeled notes and action items save hours. Product managers prototyping voice interfaces, or solo devs testing meeting bots without stitching services. Avoid if you need enterprise-scale persistence beyond optional Postgres for speakers.

Verdict

Grab it for personal or small-team use—docs and quickstarts shine, Python 3.8 setup is painless despite 18 stars and 1.0% credibility signaling early maturity. Test locally before production; lacks tests but runs stable out-of-box.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.