Feature Ideas

Automatic reminder creation that integrates with existing reminders apps such as Apple Reminders and Google Tasks

Native Android app

Being able to support other types of calendars and email clients like Outlook.

The ability to search the transcript by speaker name, date/time, location, keyword ...etc would be great for quickly making the transcript useful without having to necessarily go through the AI model.

Right now, it only captures the words. There's no indication of the sentiment or emotion. For example, I had it transcribe while I was playing a YouTube video of an SNL skit. It was about a doctor informing the family that their father didn't survive the operation. It was all humor and silliness. But from the transcript, you'd think it was a serious conversation. If Limitless could pick on on things like laughter and tone of voice to get a sense of the humor or emotion behind the words and somehow note that in the transcript, that would be awesome!

Some speaker identities in the transcription are inconsistent. For example, Speaker A is now labeled as both Speaker A and Speaker C. This likely happened because both speakers have similar voices and were mistakenly identified as the same person, especially when they talked over each other. When I try to change Speaker C back to Speaker A, it updates all instances throughout the transcription, treating Speakers A and C as the same person. Unfortunately, there doesn't seem to be a way to reset them to ensure they are identified correctly again.

Where is often as important as when and what was heard. I want to browse the timeline of my life with location, audio and video.

I would like the ability to access my data programmatically. Specifically i would like to give LLMs such as Claude the ability to read my conversations when prompted. Model context protocol would be a simple solution enabling my to directly ask claude for insights based on my Limitless conversations. As a software engineer being able to extend this data would be a massive feature and contribute to further growth as i could than build tools which rely on your platform.

I spent a reasonable amount of effort, adding speaker labels so that the diarization can work. And work well it does, once the sample size per entity is large enough. But there's only so many hours in the day, and there's dozens of people limitless hears in my audio on a weekly basis, hundreds of unique people on a monthly basis. I'm hiring an exec assistant orchestration builder to develop a larger system for me, but until then, it's me labeling the meetings I rem to label. I don't need most of those voices diarized, but I do need the people making the most salient statements (single-shot statements>salience score 'wow', or sum(salience score) > important over X weeks) who I have not labeled, or have not been recognized yet as someone who has been labeled to be surfaced in UI or even just as an API endpoint. The reasons for this are obvious, but to spell it out explicitly: important shit needs to be attributed to a known, named entity for summaries, actions, and effective management. Top 5-10 Peeps You Gotta Label Coz They Say Important Things 1-n List of 1-few statements per Top Peeps, audio playback available in content, and deeplink to day/timestamped entry where the statement was made Tricky bit, but not really tricky: make it simple for me (user) to label enough audio for that person's vocal profile to get learned as a named entity. Dopamine reward: 2-10 mins after finishing labeling a 'new' person/entity, hit me with a notification like "Jossie mentioned these 4 topics that still appear to be undecided open items of contention, 2-3 weeks after they were brought up - requires some attention"

We've had users ask for Limitless to break down the transcripts by speakers (for example: Speaker 1, Speaker 2) so they can: easily review a transcript get action items by person

i.e. Slack/Teams/Drive

Sometimes using system mic is not an option (when I'm in a public space) so I'd like to be able to record both sides of the conversation on my Windows and mobile devices.

For Rewind users, the ability to recall over an extended period of time is the ongoing value. The ability to migrate our storage to Limitless (or perhaps even export from Limitless into Rewind) would allow users to test both options and transition between them.

Record from the mobile app without a Pendant