Checking what someone said minutes ago
Mid-call, ask your employee what a specific person said earlier in the meeting instead of asking them to repeat themselves or scrolling back through your own notes.
Get a Live Meeting Transcript
Your AI employee joins a Google Meet, Zoom, or Microsoft Teams call and captures a full transcript as people speak, tagged by speaker and timestamped. Ask for it mid-call, ask for it after, or just ask what someone said ten minutes ago. When the meeting ends the transcript is saved to your employee's Drive automatically.
Your AI employee joins a Google Meet, Zoom, or Microsoft Teams call and captures a full transcript as people speak, tagged by speaker and timestamped. Ask for it mid-call, ask for it after, or just ask what someone said ten minutes ago. When the meeting ends the transcript is saved to your employee's Drive automatically.
Under the hood this is one of three angles on the same meeting bot: while the call is live, a request for the transcript pulls the segments captured so far straight from the meeting provider. The moment the meeting ends, the full transcript gets written to your employee's Drive as a speaker-tagged markdown file under a meetings folder, and every later request for it reads that saved copy instead of asking the provider again, so re-reading an old transcript never costs anything extra.
It is not the same feature as Send an Employee to Your Meeting or Meeting Summary, even though all three ride the same bot. That feature covers the employee sitting in the call and speaking when addressed; the summary feature is the automatic recap dropped in chat once the call ends. This one is specifically about the raw transcript itself, on demand, while the words are still fresh or any time after.
Getting the transcript starts with getting the employee into the call. You share the Google Meet, Zoom, or Microsoft Teams link in chat and ask it to attend; it takes about a minute to spin up, then waits in the lobby like any other guest until somebody clicks Admit. From that moment the transcript starts building, and it keeps building for as long as the employee is in the room.
How the words are captured depends on the platform, and you configure none of it. Google Meet and Microsoft Teams hand captions to participants, so those calls transcribe from the platform's own captions. Zoom does not, so those calls transcribe through the meeting provider's built in speech to text instead. Either way you ask the same question and get the same speaker tagged text back.
What this buys you is the ability to ask instead of remember. Mid call you can ask what a specific person said ten minutes ago, or exactly how a number was phrased, without asking anyone to repeat themselves or scrolling back through your own notes. After the call the same request reads the saved file, so checking a detail six weeks later works the same way as checking one six minutes later.
What gets captured
Every utterance is tagged by speaker and timestamped as it happens, not reconstructed afterward. Transcription is tuned for English audio; other languages are transcribed but less accurately. The bot is audio-only: no video feed, no screen recording, and no separate audio file is kept, only the text transcript.
During the call versus after
Ask for the transcript while the meeting is still running and the tool fetches whatever has been captured so far directly from the meeting provider, so you can check what someone said ten minutes ago without waiting for the call to end. Once the meeting ends, the full transcript is written to your employee's Drive, and any later request reads that saved file back instead of round-tripping to the provider again.
Limits and edge cases
If the bot loses connection mid-call there is no automatic reconnect; whatever was captured up to that point is what you get, a partial transcript rather than a failure. A session left running with no audio for 10 minutes, or sitting alone in an empty call for 30 seconds, ends itself so it never bleeds credits, and any live session is force-ended after 4 hours as a self-heal backstop even if the end signal never arrives. If your credits run out mid-meeting, the employee leaves the call cleanly rather than continuing to run.
How It Works
Join, transcribe, file. The record builds itself while you talk.
When the employee joins a meeting, transcription starts immediately and streams into a document in their Drive. The text builds in real time, so the record is complete the second the meeting ends.
The transcript then feeds the rest of the workflow: the automatic summary draws from it, the employee's memory absorbs it, and your team can search it or ask the employee about it later.
Because the text is the record, nothing else has to be. The employee attends audio only, with no camera and no screen share, and no audio file is kept once the call is over, only the transcript. That keeps what you store down to the part you can actually search, quote, and hand to somebody else.
Use Cases
Confirming a decision while the call is still running
Pull the live transcript to double-check exactly how a commitment or number was phrased before the meeting moves on to the next topic.
Recovering a call that dropped early
If a connection issue ends the bot's session early, the transcript captured up to that point is already saved, so you still get a usable record of the part of the meeting that happened.
Reviewing a long exchange after the fact
Once the meeting ends, open the saved transcript in Drive to reread a long back-and-forth in full rather than relying on the shorter summary alone.
Comparison
| Before | After |
|---|---|
| Notes capture fragments of what was said. | The transcript captures all of it, word for word. |
| Transcription arrives hours after the meeting. | The text streams live and is ready at the final word. |
| Recordings pile up unwatched. | Text is searchable, quotable, and feeds summaries. |
| A separate transcription subscription per seat. | Built into every employee that attends meetings. |
FAQ
Does asking for the transcript mid-call cost extra?
No. Pulling the transcript, whether during the meeting or after, is a free tool call. The only charge is the per-minute rate for the employee being present in the meeting, metered every 60 seconds while it is live.
What if the meeting bot loses connection?
There is no automatic reconnect. Whatever speech was captured before the drop is already saved, so you get a partial transcript covering the time the employee was actually on the call, not nothing.
Where does the transcript live after the meeting?
In your employee's Drive, under a meetings folder, saved as a speaker-tagged, timestamped file as soon as the call ends. It stays there for you to open, search, or hand to the employee again later.
Does this record audio or video too?
No. The employee attends audio-only with no camera or screen share, and only the text transcript is kept, not a recording of the call itself.
Can I ask my AI employee what someone said earlier in a meeting?
Yes, and you can ask while the call is still running. Your employee pulls the transcript captured so far and answers from it, so you can check exactly how something was phrased without asking anyone to repeat themselves. After the meeting the same question is answered from the transcript saved in that employee's Drive.
Does the live transcript work on Zoom, Google Meet, and Microsoft Teams?
Yes, all three. Google Meet and Microsoft Teams calls transcribe using each platform's own captions, and Zoom calls transcribe through the meeting provider's built in speech to text because Zoom does not hand captions to participants. You never choose or configure any of that; it follows automatically from the link you shared.
Is the meeting transcript tagged with who said what?
Yes. Every utterance is tagged by speaker and timestamped as it happens, rather than being reconstructed after the call, so you can see who said which line and when. The file saved to your employee's Drive keeps the same speaker tags and timestamps.
Can I get a transcript of a meeting my employee did not attend?
No. The employee has to be in the call while it is happening, so you cannot point it at a meeting that already ended and get a transcript out of it afterwards. Share the meeting link before or during the call and ask it to attend, and the transcript builds from the moment it is admitted. Transcription is tuned for English, and other languages are transcribed less accurately.
Where Get a Live Meeting Transcript fits
Get a Live Meeting Transcript is part of Things they can do out of the box.
Every AI employee ships with built-in abilities that work out of the box. Search the live web for real-time information, scrape and crawl any website for structured data, and generate images directly in conversation. No plugins to install, no APIs to configure.
- Things they can do out of the box: Research, create, and extract without plugins.
Read the guide
More in Capabilities
- Web Search: Every AI employee can search the live internet for current information and answer with sources, no setup required. It runs automatically whenever the employee needs something it does not already know, such as a competitor update, a price, or a recent news item. Results are cited titles, snippets, and URLs, synthesized into a plain answer inside the chat.
- Web Scraping: Give any employee a URL and they read the full page: article, blog post, documentation, competitor page, pricing table, whatever is public. They return clean text with the ads, navigation, and boilerplate stripped out, ready to summarize, compare, or act on. It is enabled for every employee at hire, costs no credits, and works on JavaScript-heavy pages without any setup on your side.
- Image Generation: Ask any employee to create an image and it builds a detailed prompt, generates it with an OpenAI image model, and saves the result to Drive with a persistent link. Use it for logos, social graphics, illustrations, diagrams, or landing page visuals, described in plain language. No setup required: every employee can generate images at hire, with a Model, Quality, and Shape default you can adjust per tool.
- Code Interpreter: Code Interpreter is on our roadmap: a sandboxed Python environment your AI employee will use to run scripts, crunch numbers, and transform data files on request. Instead of describing a calculation in words, you'll be able to ask for the actual computation and get back a checked result, not a guess. It is not available yet.
- Video: Hand your employee a prompt and get back a short, ready-to-post video clip, filed straight into your Drive. Built for social cuts, ad concepts, and quick product demos. Editing your own footage is coming next.
- B2B Marketplace: A network of real, vetted businesses living inside Sistava. Ask any AI employee to find a vendor, a partner, or a service provider, and it checks this network first, before it ever touches the open internet. Get listed yourself and the same network works the other way: visitors, customers, and other businesses' AI employees can discover and recommend you.
- Document Editor: Ask an employee for a spreadsheet, a report, a slide deck, or a data export, and get back a real .xlsx, .docx, .pptx, .csv, or .pdf file, not a wall of text pasted into chat. It can also revise a file you already gave it through the same chat-and-Drive workflow, keeping the work you did not ask to change intact whenever the format supports it. For PowerPoint, it can turn a brief into native slides with layouts, charts, images, shapes, tables, and speaker notes. PDFs can be polished reports or colorful, fully designed pages with professional print typography. Included with every employee on every plan, nothing extra to connect or unlock.
- Premium Prospect Database: Find real people to sell to and reveal their verified work email and phone, pulled from a premium database of over a billion professionals worldwide. Filter by role, seniority, industry, company size, and location to build a targeted list, then have your employee save the best prospects straight into your CRM. A premium add-on on paid plans; on the free plan your employee researches prospects on the open web.
- Send an Employee to Your Meeting: Share a Google Meet, Zoom, or Microsoft Teams link and your employee joins the call as a named participant. It listens, keeps a full speaker-tagged transcript, and speaks up out loud when you address it by name. When the call ends, the transcript lands in Drive and a summary shows up in chat.
- Meeting Summary: When a meeting your employee attended ends, it writes a summary and drops it in chat automatically: what got decided, who owns what, and the action items. No need to ask for a recap, it is already waiting when you check in.
- Document Text Extraction: When you attach a document to a chat message or upload it for training, your employee turns it into readable text on its own. PDFs, Word, Excel, and PowerPoint files, OpenDocument files, RTF, and plain text or data files all come through automatically, tables included, with no conversion step for you to run first.
- Import a Skill from GitHub or a URL: Paste a link to a GitHub repository or a URL that hosts an Anthropic-style Skill package, and your employee will import the whole thing directly instead of you rebuilding it by hand in the Create Skill drawer. This is on our roadmap and is not active yet: the option appears in the Skills toolbar and in the Create Skill drawer today, but importing does not run until we ship it.