Feature Requests

Having a knowledge base where we could upload documents that Hedy uses for custom prompts during meetings would help a lot. I am a data privacy professional so having legislation such as GDPR and the multitude of guidelines from Authorities within the knowledge base would allow specific recommendations following specific frameworks. The same with coaching for example. Having my own framework and process uploaded in a knowledge base would allow Hedy to be a specialised assistant in a meeting and suggest actions based on that particular framework. I am aware that this is somewhat solved by the context window and that there is an initiative for improving it, but a knowledge base goes deeper into customisation. Maybe a hybrid of the 2 could be set up for different flows.

This is a bit of a spin-off idea from the coaching/mentoring session type, but instead what I'd like to be able to do is tell Hedy at the beginning of a session what the goals/objectives are (over and above any set "agenda")... as in, some of the intangibles like establishing rapport, earn trust, demonstrating open-mindedness, gain credibility, develop buy-in/commitment, etc. The idea would be to receive feedback afterwards about how I (or whoever the user is) could have been more effective in achieving those aims, and how/why what was impactful successfully delivered the results it did, etc. There could also be the possibility for real-time Hedy-initiated "nudges" if it senses something is being overlooked or ineffectively addressed, etc.... low priority item, just sharing the idea/concept. We could arguably bake the post-session feedback piece into existing session formats using a custom prompt, but I assume the proactive platform-initiated 'nudging' concept might be a bit more of a lift to develop. Thoughts?

First, I would like to be able to export a topic or multiple topics. To break it down: When I select a topic to export, I want to be able to perform a bulk export of multiple sessions within that topic. When I export a topic, I should be able to select either all or some of the sessions within that topic. Even within the sessions, I want to be able to drill down and select whether to export the entire data, just the summary, just the to-dos, or the detailed notes. Therefore, all of these options should be available for export per session and per topic.

Right now you can only copy chat entries. It would be nice to have more options like delete or add to summary.

As a meeting participant, I want to provide images (via upload, camera, or paste) and PDFs during a session so Hedy can offer insights, and ensure all these assets are bundled into the final session data sent via webhook. Input Methods (Upload & Paste) * AC 1.1: The chat interface must support Cmd+V / Ctrl+V to allow users to paste images directly from their clipboard (e.g., from a screenshot tool). * AC 1.2: Users must be able to upload files in PDF, PNG, and JPEG formats via a file picker. * AC 1.3: On mobile, the interface must allow capturing a photo via the system camera for immediate upload. * AC 1.4: The UI must show a "processing" state or thumbnail preview while the file is being analyzed by the AI. Real-Time AI Insight * AC 2.1: Hedy must use the uploaded/pasted content as primary context for subsequent chat queries. * AC 2.2: Hedy must be able to perform OCR (Optical Character Recognition) and data extraction to answer specific questions about the shared file. * AC 2.3: If multiple files are uploaded, Hedy must maintain a "session memory" of all files shared within that specific meeting. Session Ended Webhook Integration * AC 3.1: The system must trigger a session_ended webhook only after the meeting is concluded. * AC 3.2: The webhook payload must include a files array containing all assets shared during the session. * AC 3.3: Each object in the files array must contain: * original_filename * file_type (MIME type) * storage_url (A secure link to the file) * timestamp_pasted (When it was introduced to the chat) * AC 3.4: The webhook must also include the full_transcript and ai_summary alongside the file data to provide a complete historical record.

It would be nice to highlight terms and words in the transcript text using a search function. Some of the sessions I’m using are very long, and I’m trying to find context for some of the things being said.

Add post-meeting voice attribution that allows users to tag speakers by name and role, then automatically recognize those voices in future meetings. With saved background and org context (pro feature)(titles, reporting relationships, frequent collaborators), Hedy AI could generate summaries, action items, and follow-ups with names already attached and better prioritization. This would move Hedy beyond transcription into true meeting intelligence by understanding who is speaking and how their role impacts decisions and next steps.

Integration with Apple Reminders would be amazing and/or a centralized location to see all to-dos (sort-/filterable by open/closed/date, etc) would be wonderful!

Hi there, I teach English as a foreign language and I’m trying to record my lessons to create actionable summaries for my students. We often speak English and French during our lessons. Currently, it only transcribes English, but it would be fantastic if it could also transcribe other languages. Thanks for your incredible work!

In addition to the current basic local Whisper model, it could be added Parakeet as ASR model option, which offers excellent performance with low-latency, especially for European languages, the primary user base of Hedy AI. Parakeet is highly efficient, requires only 1GB of storage and runs well on mid‑range devices manufactured in/since 2024, making it a valuable upgrade for improved local transcription quality, even offline. Note: An optimized speaker-identification workflow can be envision with Parakeet generated transcripts being sequentiallly processed by Sortformer, Nvidia's state of the art model for speaker diarization . Currently, Sortformer v2.1 identifies up to 4 speakers, neverthless an 8-speaker version , better suited for meetings, is in progress with an ETA in Q2 2026