Feature
Meetings produce decisions, but those decisions only matter if someone captures and follows up. VidNotes analyzes meeting transcripts to automatically pull out action items, decisions, owners, and deadlines. Instead of relying on manual note-taking during the call, you can focus on the conversation and let VidNotes extract the commitments after. What you get is a clean, organized list of next steps you can export and share with your team. After a 30-minute sprint planning meeting where six tasks were assigned across four team members with different deadlines, VidNotes will produce a structured list with each task, its owner, and the stated deadline, all linked to the timestamps where each commitment was made. The extraction uses OpenAI models through AIProxy with prompts built to spot commitment language, separate firm decisions from hypothetical chatter, and attribute tasks to the right speakers.
Record your meeting and import it into VidNotes, or paste a link if it was recorded on a platform like Zoom, Teams, or Google Meet. The transcription captures everything said with timestamps, keeping the full context around each decision. You can import from your device, iCloud Drive, Google Drive, or Dropbox. For meetings recorded as video calls, the audio extraction pipeline handles the compressed audio codecs that meeting platforms typically use.
After transcription, tap the action items option. The AIProcessingService reads the full transcript, spots commitments, decisions, and assigned tasks via linguistic pattern recognition, and pulls them into a structured list. It tells the difference between firm commitments ('I will send the report by Friday') and hypotheticals ('We might want to consider updating the docs'), so only real action items make it into the output. Each item includes a description, the mentioned owner, and a deadline when one was stated.
Review the extracted items, make any edits, and export the list as PDF or TXT. Share with your team through email, Slack, or your project management tool via the iOS share sheet. Each action item links back to its source timestamp, so if there's any ambiguity about what was agreed, you or your team can tap through to hear the original conversation in context instead of debating what the notes meant.
Project managers
Get a clean list of action items after every meeting without relying on someone to take notes. Import straight into your project management workflow by exporting as TXT and pasting into Jira, Asana, or Linear. Use the timestamp links to settle disputes about what was agreed when stakeholders remember the conversation differently.
Team leads
Share a concise summary of decisions and next steps with your team, including who owns each item and when it's due. Replace the post-meeting scramble to reconstruct what was said with a single tap that produces a shareable, accurate record of commitments made during the call.
Remote teams
Keep alignment across time zones by sharing action item summaries from recorded meetings with team members who couldn't attend live. Remote teammates get the same clarity as attendees, with the option to tap into the original recording at any action item's timestamp to hear the full discussion context.
The extraction engine looks for linguistic patterns that signal commitments: phrases like 'I will', 'we need to', 'by Friday', 'let us schedule', 'the decision is'. It reads context, so a hypothetical chat about what someone might do gets treated differently from a firm commitment. The AI also catches delegation patterns ('Can you handle the client follow-up?'), conditional commitments ('If the budget is approved, we will hire two more engineers'), and implicit deadlines ('before the next sprint' or 'by end of quarter'). That contextual reading produces a focused list of real action items rather than a noisy dump of every sentence with a future-tense verb.
Each extracted action item is stored as a SwiftData ActionItem entity linked to the original VideoTranscript through a one-to-many relationship. This keeps the connection between the action item and the full context of the discussion, so you can always go back and listen to the exact moment a decision was made. The ActionItem entity stores the task description, owner attribution, deadline, and source timestamp. Since these are persistent local entities, your action item history builds up across meetings, giving you a searchable record of commitments over time.
Action items come back in the language of the transcript via the AIProcessingService's language-aware prompt system. If your team meets in German, the extracted items will be in German with proper business terminology preserved. The language-specific prompts account for how commitments get expressed differently across languages and cultures, like the more indirect phrasing common in Japanese business meetings versus the explicit assignment patterns typical in English-language standups. That linguistic awareness cuts down on false negatives where commitments phrased in culturally specific ways might otherwise slip through.
Start with a free account. Paste a video link and see it in action.