# wendy7756/AI-Video-Transcriber

Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages.

Repository: https://github.com/wendy7756/AI-Video-Transcriber
Canonical: https://ross.abutalabs.com/products/ai-video-transcriber
Homepage: https://sipsip.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: aitool, tiktok, transcribe, videototext, youtube
Last push: 2026-08-23T16:15:21+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 26
- inputs: {"age_days": 370, "days_push": 10, "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 3215, forks 409 (observed 2026-08-28T04:07:49.369945+00:00)

## What it is
An open-source AI tool that transcribes, summarizes, and archives videos and podcasts from 30+ platforms (YouTube, TikTok, Bilibili, etc.) or local files. It uses a subtitle-first architecture with Faster-Whisper as fallback, plus LLM-based text optimization and multi-language summaries via any OpenAI-compatible API.

## Use cases
- transcribe youtube videos to text
- summarize podcasts with ai
- convert tiktok videos to transcripts
- transcribe local audio and video files
- generate summaries in multiple languages
- get transcripts without downloading audio
- self-host a video transcription service

## When to choose
- you need transcripts from many video/podcast platforms via URL
- you want subtitle extraction first for speed with Whisper fallback
- you prefer bringing your own OpenAI-compatible API key or local LLM
- you want a self-hosted, multi-language transcription and summarization pipeline

## When to avoid
- you need a fully managed hosted service with daily briefs and knowledge base features
- you have no access to any OpenAI-compatible LLM API
- you need real-time live captioning rather than batch transcription
- you require speaker diarization or word-level timestamps

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, video-processing, audio-processing, http-server
- domain: artificial-intelligence, speech-processing, media, developer-tools, self-hosted
- platform: python, self-hosted, cross-platform
- tags: whisper, yt-dlp, transcription, summarization, podcasts, youtube, fastapi, openai-compatible, subtitles, ffmpeg, natural-language-processing, video, audio, web-server, docker

## Member repositories
- wendy7756/AI-Video-Transcriber (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.369945+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 2026-08-29T18:44:56.686351+00:00, confidence not recorded.
  - readme: https://github.com/wendy7756/AI-Video-Transcriber (fetched 2026-08-28T04:07:49.369945+00:00, sha 162ba597cc92)
  - homepage: https://sipsip.ai (fetched 2026-08-29T09:38:11.670106+00:00, sha c4f65173e372)
  - site_page: https://sipsip.ai/about (fetched 2026-08-29T09:38:11.680595+00:00, sha cd00795ae741)
  - site_page: https://sipsip.ai/pricing (fetched 2026-08-29T09:38:11.678913+00:00, sha 94ce1fd4af1d)
  - site_page: https://sipsip.ai/changelog (fetched 2026-08-29T09:38:11.682485+00:00, sha b7acc085804a)
- Data as of 2026-08-30T08:39:29.467469+00:00.