Obsidian plugins with #transcription#

The YTranscript plugin is a game-changer for Obsidian users who frequently watch YouTube videos and take notes. With this plugin, you can easily extract transcripts from selected YouTube links and view them in a side window with timestamped markers. You can customize the frequency of timestamps and even copy all text or drag-and-drop lines to add to your notes. The plugin also allows you to click on timestamps to jump to specific points in the video, making it a powerful tool for note-taking and research.

The Transcription plugin enables users to generate high-quality text transcriptions from a variety of audio and video file formats, utilizing advanced speech-to-text technology. It supports multiple transcription engines, including cloud-based Swiftink.io, which offers domain-aware, free, high-quality transcriptions, and Whisper ASR, an open-source local option. Users can transcribe multiple files simultaneously, access start and end timestamps for each transcribed line, and work with the transcriptions in the background. Additionally, Swiftink.io provides summaries, outlines, and notes for each transcription, enhancing the productivity and organization of transcribed content.

The Epiphany plugin enables seamless integration between your Obsidian vault and the Epiphany Voice app, allowing users to quickly transcribe and sync voice notes from their iPhone or Apple Watch directly into Obsidian. It supports sending notes to a default location or creating separate notes for each recording, providing flexibility in organization. The plugin periodically fetches new transcriptions, ensuring your vault stays updated, and includes manual sync options for added control.

The Gladdis plugin enhances Obsidian by integrating AI capabilities for writing, transcription, and content processing. It supports conversational interactions in Markdown, audio transcription via Whisper, and document loading from text, PDF, or web sources. Users can create named system prompts and assign different AI personalities for versatile workflows. Gladdis is compatible with OpenAI models and local open-source options, offering tools for vision, text processing, and transcription. The plugin is ideal for users seeking to enhance their productivity with AI-driven features while maintaining Obsidian's native Markdown workflow.

The AudioPen Sync plugin seamlessly integrates Obsidian with AudioPen and VoiceNotes, allowing users to transcribe audio files and save them directly into their notes. It uses webhooks for automatic or manual synchronization, enabling efficient management of transcribed content. The plugin supports custom templates for note creation, offering flexibility in formatting with placeholders for metadata like tags, transcript, and creation date. This tool is ideal for users who frequently create audio notes and need a streamlined way to integrate them into their Obsidian workflow.

The Audio Notes plugin helps users take notes while listening to audio files such as podcasts. It enables the creation of timestamped audio notes that contain embedded audio players for replaying specific quotes. Users can generate transcripts, set playback speeds, and specify start and end times for their notes. The plugin supports integration with transcription services and allows hotkey customization for easier playback control. With mobile support, users can capture thoughts on the go and sync them across devices.

The Note Companion plugin combines AI chat, transcription and file organization in one workflow for turning rough captures into cleaner notes. It can transcribe YouTube videos plus local audio or video files, chat with vault context using files, folders and tags, suggest folders, tags, titles and formatting for messy notes, and enhance meeting notes with transcripts, discussion points and action items. The plugin supports Note Companion Cloud as well as a self hosted backend, and it can run with several model providers including OpenAI, Claude, Gemini, Groq and local Ollama based setups. It stays desktop only, with setup paths that change depending on whether AI runs through the hosted service or infrastructure you control yourself.

The SystemSculpt AI plugin brings an agent workspace into notes with chat over files, images and built in vault tools. It streams reasoning, citations, tool activity and approval steps instead of hiding them. Conversations can include mixed attachments, and the plugin can find related notes through a portable semantic index. It also handles audio capture, imported audio and YouTube processing, then turns them into Markdown or SRT transcripts with structured summaries. Studio adds visual workflows for text, images, documents, media and vault actions. The same setup runs on desktop and mobile, while local CLI, terminal, dataset adapter and FFmpeg nodes stay desktop only. AI requests go through the SystemSculpt API, and vault mutations can pause for approval or run with full access.

The TikToker plugin saves TikTok links as notes with embedded playback, pulled metadata, hashtags, and flexible templates for file names and note content. Notes can open immediately after capture, duplicates are handled with prompts and batch processing helps when several links are queued. The review queue is a big part of the plugin. It adds sidebar based browsing with filters, sorting, progress tracking, starring, watched status, review again tags, quick notes, inline editing and Dataview query support.

The Obsidian Offline Whisper Transcription plugin adds local voice transcription to notes using Whisper models, with a setup that changes by device so it can stay usable across desktop and mobile. On Windows, macOS, and Linux it downloads a matching `whisper.cpp` binary on first use, while on Android and iOS it runs a bundled transformers.js build through WebAssembly. You can pick the model in settings, then start or stop capture from the ribbon or command palette when you want to dictate into a note. Audio stays on the device and is not sent to remote servers.