Feature Ideas

Create a saved library of speaker names for quick selection. Ideally, this feature would work with voice recognition so Hinote can automatically match and assign the correct name from the library based on the speaker’s voice.

I have the same people in meetings after but I have to name them each time. Otter ai has auto-speaker detection which is great. Would love to see this added.

While in a call if by mistake you interrupt recording and then start again to record, it will be helpful to have a feature to directly be able to combine multiple recordings and compile for 1 summary.

Whisper mode has enormous potential, but in its current state, it's not particularly useful. I want to spend my day dictating ideas, notes, tasks, and appointments, with this information automatically organizing itself into my existing workflow. Current Problem: Right now, I avoid using Whisper mode entirely because captured content gets stored indefinitely without any way to integrate it into my productivity systems. This creates a data silo that defeats the purpose of quick voice capture. What I Need: Tool Integration: Direct connections to platforms like Notion, Todoist, Google Calendar, Readwise, etc. Smart Routing: Automatic categorization and routing of dictated content (notes → Notion, tasks → task manager, appointments → calendar) Actionable Output: Voice captures should become immediately usable in my existing workflow, not isolated text files Why This Matters: Voice capture should enhance productivity, not create additional work. Without integration capabilities, Whisper mode is just another disconnected tool that requires manual transfer of information—exactly what voice input should eliminate. The goal is seamless capture-to-action: speak an idea, and have it automatically appear in the right place in my productivity ecosystem.

I would love for whisper notes to be an integrated experience. For example, if I am using it over the course of a week and I make notes 5 times for things to add to my calendar, 15 to do items for work, 7 shopping list items, and 18 random ideas I would prefer these be processed into a single document with headings rather than 45 separate whisper notes BECAUSE 45 notes does not help me organize my life and makes processing the notes even more burdensome. I would also suggest that this be a “rolling” or living document in which perhaps everything is added as a checklist item (perhaps with date/time stamp) under the heading so as I complete the task or move a crazy idea into a more solid document (or decode it is too crazy and do not want to pursue it) I can check the box to send it to the bottom of the document or to an archived section.

I already pay subscriptions for OpenAI, Claude & Gemini. Allow me to leverage those for my transcription vs having to buy credits from you.

It would be great to offer an optional mind map-style summary, similar to what PLAUD AI provides. This format gives a clear and visual structure to the conversation—breaking down key topics, subtopics, and connections between ideas. For users dealing with complex calls or meetings, a mind map can improve understanding, memory retention, and even presentation to colleagues or clients.

It would be helpful to have Start, Stop, and Pause buttons on the application instead of having to press the checkmark button on the device itself.

It would be great to have the ability auto upload transcripts or meeting summaries to a 3rd party service like OneNote, google drive, Notion, Confluence, or other note taking apps that we likely use for our meetings or keeping track of things. I personally would like OneNote but I am looking at Notion as getting approval to integrate with OneNote for work might be hard.

Would be nice to be able to change date/time formats for local usage (like AM/PM for time and MM-DD-YYYY)

I Think it would be great if you consider a To Do or Planner Integration. The To do Points should be transferred automaticly to the To do list.

Transcription-only should be available even with the Pro plan. Specifically, we would like to allow users to transcribe recordings for free without speaker diarization, and then upgrade to include speaker identification and AI-generated summaries only if needed. The reason is that simply being able to read the transcription helps users quickly understand the content without having to replay the audio each time. This way, they can decide whether it's worth applying the Pro plan features to a particular recording. It allows users to avoid unnecessary costs and save their remaining Pro plan credits for recordings that truly need advanced processing.

Ability to select multiple notes(after transcribe and summary) from home screen to export in some format, like TXT. The main use case is for the user has multiple meetings where a project is mentioned and he would like to use the transcript from each meeting to run through another LLM to get a summary of certain project which is talked about/ mentioned in each transcipt. currently, user does not have a method to select multiple transcript to export, this needs to be done one-by-one.

I use whispers while I-m reading to remind phrases I like from that book, so organize them in different folder by book would be super helpful