Meeting Transcription, Captions, and Recording for Mac
Voxt supports three meeting audio modes: Meeting for system audio plus microphone, Captions for system audio only, and Recording for microphone only. During a session, it can transcribe and translate in real time; afterward, review speakers and timestamps, generate a summary, analyze the conversation, and ask follow-up questions.
At a glance
- Choose Meeting, Captions, or Recording mode for the audio sources you need.
- Follow real-time transcription and translation while the session is in progress.
- Review speakers and timestamps after the meeting ends.
- Use summaries, analysis, and follow-up questions to turn the transcript into next steps.
- Import existing audio or video recordings for queued meeting-file analysis.
Three modes for different audio sources
The mode determines which audio Voxt captures. Choose the smallest source set that matches the meeting so the transcript reflects the conversation you need to understand.
Meeting mode
Capture system audio and microphone audio together for a conversation where you need both the other participants and your own voice.
Captions mode
Capture system audio only for live captions of a call, video, presentation, or other audio playing through the Mac.
Recording mode
Capture microphone audio only for a personal recording, interview, voice memo, or in-room conversation.
From live transcript to useful meeting record
A meeting transcript is most valuable after the call, when it can answer what was said, who said it, and what should happen next.
Real-time transcription and translation
Follow the conversation as text while the session is happening, with real-time translation available for multilingual meetings.
Speakers and timestamps
Review the finished meeting with speaker information and timestamp context so important moments are easier to find.
Summary, analysis, and follow-up
Ask for a meeting summary or analysis, then ask follow-up questions against the meeting result to recover decisions, open questions, and next actions.
Analyze an existing recording
The same meeting review workflow can start from a recording that already exists on your Mac. This is useful for interviews, lectures, presentations, and calls saved as audio or video.
Drop in audio or video
Choose or drag a supported recording into the file workflow. Voxt prepares the audio track before running the selected transcription pipeline.
Process a long file in the background
Imported recordings use a queued file-analysis path with progress, cancellation, retry, and prioritization controls. The current supported duration is up to 12 hours per file.
Review the result like a meeting
Open the completed result to inspect speakers and timestamps, generate a summary, analyze the conversation, and ask follow-up questions.
FAQ
What is the difference between Meeting, Captions, and Recording mode?
Meeting mode captures system audio and microphone audio, Captions mode captures system audio only, and Recording mode captures microphone audio only. Choose based on which speakers or audio source you need in the transcript.
Does Voxt transcribe meetings in real time?
Yes. Voxt can provide real-time transcription during a meeting session, with real-time translation available as part of the meeting workflow. Actual timing depends on the selected model and audio conditions.
Can I see speakers and timestamps after a meeting?
Yes. Meeting details can include speaker information and timestamps so you can review who said what and return to important points in the conversation.
Can I ask questions about a meeting afterward?
Yes. After the meeting, use the result for summary and analysis, then ask follow-up questions about decisions, action items, unresolved topics, or other details in the recorded conversation.