# harry0703/AudioNotes

快速提取音视频内容，整理成一份结构化的markdown笔记

Repository: https://github.com/harry0703/AudioNotes
Canonical: https://ross.abutalabs.com/products/audionotes
Language: Python
License: MIT
License Family: permissive
Topics: ai, asr, funasr, ollama, python, qwen2, whisper
Last push: 2026-08-19T06:15:03+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 55
- inputs: {"age_days": 775, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2472, forks 365 (observed 2026-08-28T04:06:54.778324+00:00)

## What it is
AudioNotes is a locally-run web application that transcribes audio and video files into text and organizes them into structured Markdown notes. It uses FunASR for on-device speech recognition and Ollama-hosted LLMs (e.g., Qwen) for note generation and follow-up Q&A, keeping all data on the user's machine.

## Use cases
- transcribe meeting recordings into structured notes
- convert lecture audio to markdown notes
- summarize interview recordings automatically
- chat with the content of an audio or video file
- record voice memos in browser and get transcripts
- transcribe audio offline without sending data to cloud AI

## When to choose
- you need privacy-first, fully local transcription and note-taking
- you work with Chinese-language audio and want high recognition quality
- you want to ask follow-up questions about meeting or lecture content
- you prefer self-hosted tools with Docker deployment

## When to avoid
- you need cloud-scale or multi-language enterprise transcription
- your machine lacks 12-16GB RAM for Docker and local models
- you need real-time streaming transcription during live events
- you want a hosted service with no local setup

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, chatbot, markdown
- domain: speech-processing, developer-tools, self-hosted, privacy
- platform: self-hosted, cross-platform, python
- tags: asr, funasr, ollama, whisper, meeting-notes, transcription, local-first, audio-to-text, video-to-text, chainlit, natural-language-processing, docker, web-server

## Member repositories
- harry0703/AudioNotes (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:54.778324+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:28:32.525602+00:00, confidence not recorded.
  - readme: https://github.com/harry0703/AudioNotes (fetched 2026-08-28T04:06:54.778324+00:00, sha 5e02c083e66e)
- Data as of 2026-08-30T08:39:29.467469+00:00.