#62 · Primary category: Speech & Audio
AI-Video-Transcriber
Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages.
Project last updated:08/23/26
GitHub Stars
3.2K
Forks
416
Contributors
1
License
Apache-2.0
Why we included this project
Most video transcription tools either force you to upload files or only handle one platform. This one accepts a URL from YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, or 30+ other sources, and also lets you drag in local audio, video, or even plain text files. When a platform has native subtitles, it grabs those instantly and skips audio processing entirely, falling back to Faster-Whisper speech recognition only when no caption track exists. After transcription, the pipeline fixes typos, completes truncated sentences, and can produce summaries in a language of your choice, auto-translating when the source and target differ. You can point it at any OpenAI-compatible API endpoint from the UI, so it works with a local model or a hosted provider. That makes it a practical tool for anyone with a backlog of recordings, lectures, or meeting notes who wants clean, structured text instead of more hours of playback.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production