Feature Ideas

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

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.

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 think it would be helpful if we could ask questions about the meeting content. For example, a question like “What was the date and time Mr. A suggested regarding ○○?” It would be great if the system could answer based on the transcript. To prevent hallucinations, I would like the answer to include the specific part of the transcript it was based on.

New to the service and realised I had forgotten to stop and start a new meeting recording, so have two separate meetings in one audio file. This of course means the transcription and the summary is then incorrect. It would be good to be able to highlight the split and refactor the Summary notes

I would love a place to find all my action items or followups. The summaries are great at generating next-steps and follow ups, but I have to click on each individual meeting and scroll to find them. It would be great if I could see all my check-boxes in one place in the app. Bonus points if I can sync those to something like Google Keep or Asana.

I use my HiDock P1 a lot, and I thinking if the folder navigation could be improved in a way where you can have sub folders for certain things. Example: [Class A] [topic 1] [Topic 2] Or Company 1 - legal meetings - marketing meetings - etc

All our context doesn’t always come from meetings. Sometimes we need information from external sources, from ideas we’ve developed across multiple inputs. We also use our AIs as a second brain, ping-ponging ideas and refining concepts iteratively. To have the full picture, we need to centralize that context instead of fragmenting it across tools. That’s why I’m proposing either enabling integration between our AIs here, or establishing a direct and secure data flow between systems. This would allow us to maintain continuity, preserve institutional knowledge, and improve decision-making without duplicating effort or losing context

I want to create an agent on my OpenClaw server to download recording and summaries in a more programatic way (vs. just scraping the web browser) and take various actions on my behalf. This could be done in a number of other ways but a more seamless and secure approach would be ideal. This could be done via an API and using a secure token for example.

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.

In the “Recordings” tab, all files currently have default names like “20250604-161356-Rec87.hda,” which makes it hard to identify them quickly. It would be very helpful to allow users to rename a recording manually before summarizing it, directly from the interface. This small improvement would make it easier to organize and locate specific meetings, especially for users handling multiple recordings per day.

Guys, I love this product and would like to purchase it. The only thing that concerns me is the lack of the ask-ai feature, which allows us to speed up our workflow by avoiding having to listen every time we have a question, when we could simply ask and get an answer. To be honest, that's why I continue to use Otter.ai, even though it doesn't have the ability to record audio using AirPods. Please consider adding this feature and you will gain more and more customers. Thanks

The speaker identification feature really should be included for free. Without it, the transcripts lose much of their value because you can’t properly tell who said what. Honestly, it doesn’t look like a high-cost feature from the provider’s side, but without it the device feels incomplete and borderline unusable. Charging extra for something so essential feels wrong and makes the overall product less compelling.

Please give a lifetime membership discount for Kickstarter backer

As I'm still a new user of P1, I had forgotten to stop the recording till much later. But it was through this mistake that I realized there is no ability to edit recordings. Ability trim recording becomes useful in such cases. Functionality to split recordings can also be useful when there are back-to-back meetings.