Captions inside the meeting app
- What it is good at
- Nothing to install, already there when the call starts.
- Where it runs out
- Tied to that one app, and the meeting usually ends with captions rather than a record you can go back and correct.
KaigiFlow
Every voice, understood.
Make room for a shared understanding.
Wherever the conversation happens.
In the room. Across the screen. In the audience.
Illustrative scenes. Product demonstrations use real app recordings.
Verified at a glance
No bot
Captures your microphone or Mac system audio instead of joining the call
On your Mac
On-device: nothing about the meeting leaves the device.
Translation alone is not a shared understanding
Multilingual meetings get handled in four broad ways. Each one fails differently, and the difference is usually about what you are left holding when the call ends.
A meeting bot
- What it is good at
- Captures the call reliably and works the same way every time.
- Where it runs out
- Everyone can see it join. Plenty of clients, employers, and regulated conversations will not allow an extra participant.
A human interpreter
- What it is good at
- The highest-fidelity option when the conversation genuinely matters.
- Where it runs out
- Booked ahead and priced per session — hard to justify for an ordinary recurring call.
KaigiFlow
- What it is good at
- Captures your microphone or your Mac's system audio, so nothing joins the call. Keeps the recording on your Mac.
- Where it runs out
- Mac with Apple silicon only, and capturing system audio needs the macOS Screen & System Audio Recording permission.
Compared by how each approach is used, not by vendor. KaigiFlow's row is the only one this site makes product claims about — and every claim in it is checked against the current build before this page can be built.
A SHARED THREAD
Different languages. One conversation.
An interactive illustration, not an app recording. Names, voices and meeting content are fictional.
Synthetic sample
The welcome workshop
Choose a sentence to replay its sample audio.
Follow the meeting as it happens
Point KaigiFlow at your microphone or your Mac's system audio. Speaker-labelled text appears live as people talk — no bot joins the call.
- Choose your microphone or Mac system audio as the capture source.
- Watch live transcription appear with stable speaker labels.
- Read up to three selected output languages alongside the original.
- Pause and resume without losing the conversation.
- Keep the recording on your Mac the whole time.
One meeting — before, during, and after
KaigiFlow carries a single continuous record from setup to export.
Before
Set the input language, pick up to three outputs, add participants, and choose the capture source.
During
Read live transcription and translation with stable speaker labels. Pause when you need to. The recording stays on your Mac.
After
Replay any sentence, confirm speakers, retranscribe, retranslate, rename, and export the revision you choose.
Know who spoke — without guessing
KaigiFlow separates speakers as the meeting happens and helps you confirm them afterward. Uncertain speakers stay unresolved until you decide.
- Designed for meetings of two to eight speakers.
- Import participant lists from text, images, or PDFs.
- Confirm speakers manually, or save voice samples for people you meet often.
- Automatic remapping is confidence-aware and always reviewable.
Replay the exact sentence. Keep the revision you trust.
Select any line in the transcript and the audio jumps to that moment.
- Playback follows the active sentence as you listen.
- Switch between the live and refined transcript and translation revisions.
- Exports reflect the revisions you selected.
YOUR MEETING, YOUR SETUP
Make room for understanding.
Find the setup that fits your meetings. Check device availability and beta details before you begin.
Explore devicesPrivacy you can draw on one line
The flow is short enough to state exactly.
- Microphone or Mac audio
- Local recording
- Local transcription and speaker processing
Sangei Cloud
Live translation sends text to Sangei Cloud, not audio. Re-read and imports using Sangei Cloud upload recordings when you choose those features.
Languages, verified before we list them
Choose the right language setup for your conversations.
Language coverage depends on the app build. Contact support for current availability. Language support
When you will reach for it
Four moments that create the need. Not four job titles.
When the meeting switches languages
An English–Japanese call keeps moving between both languages and nobody wants to stop for a summary. Follow both sides while it is happening.
When you cannot add a bot to the call
A client, an employer, or a policy rules out a visible extra participant. Capture your Mac's system audio from a Zoom or Teams call instead — nothing joins the meeting.
When several people speak and you lose the thread
Prepare the participant list beforehand, keep speaker labels stable through the conversation, and confirm anyone uncertain once it is over.
When you need one reliable record afterwards
Replay the exact sentence, retranscribe and retranslate what matters, and export the revision you actually trust.
KaigiFlow
Every voice, understood.
Film preview — coming soon
Evidence before adjectives
Every numeric or compatibility claim on this site is backed by a dated internal record. What we cannot verify, we do not say.
9
Capabilities with dated evidence
2026-08-17
Verification date
2026-11-17
Re-verification due
KaigiFlow at a glance
- KaigiFlow, by Sangei AI Limited (Hong Kong)
- KaigiFlow transcribes and translates meetings live, with transcripts you can review after the meeting.
- KaigiFlow has apps for Mac, iPhone and Apple Watch. The Mac app is in beta.
- You can follow up to three text outputs at once. Contact support for language availability in your app build.
- This website has 11 interface languages. Website languages and supported meeting languages are separate lists.
- Recordings, transcripts and voice profiles stay on your device unless you export them or use the cloud features described in the Privacy Policy.
- Live cloud translation sends text, not audio. Re-read and cloud imports upload recordings; cloud reports send transcripts.
- Join the beta email list on the download page for invitations and beta news. You can leave the list at any time.
Questions people ask
Meeting capture, supported languages and what happens to your recordings.
Does KaigiFlow join my Zoom call?
No. KaigiFlow captures your microphone or your Mac’s system audio, so it does not join the meeting as an extra participant. You can use that capture with a meeting running on your Mac. Tell the other participants you are recording and obtain any consent required where you meet.
Does my audio leave my Mac?
When you use Sangei Cloud, live translation sends text, not audio. Recordings stay on your device unless you export them or use a feature that uploads them. Re-read and imports using Sangei Cloud send recordings for transcription. The Privacy Policy explains these choices, cloud reports and how long information is kept.
How is KaigiFlow different from a meeting bot or built-in captions?
KaigiFlow captures audio on your Mac without adding a participant to the call. It gives you speaker-labelled transcription and translation, then lets you review the meeting afterward. Capture uses your microphone or Mac system audio rather than an integration with one meeting service. System audio capture requires the relevant macOS permission.
Which languages does KaigiFlow support?
You can follow up to three text outputs at once. Available meeting languages depend on your app build, so contact support for the current list. Input, text translation and spoken output are different settings. The website’s 11 interface languages do not establish which meeting languages your app supports.
Can I delete my meeting recordings?
Yes. You can delete meetings and voice profiles in the app. Recordings and other local meeting information remain on your device unless you export them or use the cloud features described in the Privacy Policy. Exported files are yours to manage separately. Cloud processing follows the retention periods in that policy.
Can KaigiFlow tell who is speaking?
KaigiFlow separates speakers during a meeting and can use voice samples you save for people you meet regularly. Speaker labels are assistive, not biometric identification. Uncertain speakers remain unresolved until you confirm them. Review speaker assignments after the meeting instead of treating every automatically assigned name as a confirmed identity.
Is there an iPhone app?
Yes. KaigiFlow has apps for Mac, iPhone and Apple Watch. The devices page shows the Mac and iPhone interfaces using real app screens. The Mac app is in beta; the download page explains current beta availability. Do not assume that every feature or release stage is identical across platforms.
How do I join the KaigiFlow beta?
Open the download page, enter your email address and select the checkbox for beta invitations and news. Joining the list does not guarantee an invitation or a release date. You can leave using the withdrawal form on that page. Privacy Policy section 7 explains the list’s purpose and retention.
Bring clarity to your next multilingual meeting.
See the Mac beta details — status, compatibility, and install notes for the private beta.
Mac beta details