Obsidian plugins with #audio-transcription#

The Resojot plugin brings audio capture, transcription and note processing into one workflow for spoken notes. It saves recordings inside the vault, turns them into Markdown notes and supports different writing modes such as new notes, append flows and journal oriented placement. The plugin can route speech through local or cloud ASR providers, then pass the result through custom LLM polishing steps to extract todos or generate short summaries. It also handles imported audio, long recordings, task recovery and fallback provider switching when a service fails.

The AI Commander plugin integrates OpenAI's GPT models with Bing search and other AI tools to enhance note creation and management in Obsidian. Users can generate text, images, or audio transcripts based on prompts, selected text, or current lines. It supports contextual text generation using Bing search results or embedded PDF attachments. Features include customizable commands, prompt optimization through Prompt Perfect, and compatibility with Whisper and DALL·E models for audio and image generation. This plugin is ideal for leveraging AI to streamline content creation and enrich notes.

The Transcription Audio (Beta) plugin converts linked audio files into structured Markdown content directly within your notes. It automatically detects audio links or embeds in the active note, sends the file to Google Gemini for transcription and summarisation and inserts the generated text exactly where your cursor was placed. A dedicated rightside progress panel shows each step in real time, including file details, request timing and success or error states, so you always know what is happening. The workflow is simple and command driven, designed to keep you focused on writing rather than managing files.