> ## Documentation Index
> Fetch the complete documentation index at: https://miniti.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# transcription

> real-time speech-to-text with deepgram nova-3 in 11 languages

miniti transcribes your meetings in real time using **deepgram nova-3** with \~200ms latency. it supports 11 languages, separates speakers by audio source, and can diarize multiple remote speakers.

## how it works

there are two audio sources:

* **microphone** - your voice. always labeled **"you"** in the transcript (green).
* **system audio** - audio playing through your mac (zoom, meet, teams, etc.). remote speakers are labeled **"speaker 1"**, **"speaker 2"**, ... (blue).

on macos, mic and system audio are transcribed on separate channels. your mic stays **"you"**; remote speakers stay on the system channel, even when speech overlaps. that is clearer than mixing both into one mono stream.

<Note>
  acoustic loopback can still put your voice on the system channel if speakers bleed into the room mic path. headphones reduce that.
</Note>

this source-based separation means you always know who said what, even before any ai insights run.

<Note>
  on ios, there is no system audio capture. ios transcribes the microphone only.
</Note>

## personal dictionary

add product names, acronyms, and uncommon words in **settings**. miniti boosts those terms during live transcription on both macos and ios.

the dictionary sits alongside built-in and calendar terms. total capacity is about **100 terms**.

## calendar boost

when a meeting comes from google calendar, the event title and attendee names help transcription recognize people and companies more accurately. non-consumer email domains (for example `acme.com`) are included when available. see [google calendar](/docs/integrations/google-calendar).

## supported languages

set a default in settings or pick per meeting from the language dropdown before recording. transcription, insights, and filler-word detection all adapt to the selected language.

| language   | code |
| ---------- | ---- |
| english    | en   |
| español    | es   |
| français   | fr   |
| deutsch    | de   |
| português  | pt   |
| italiano   | it   |
| nederlands | nl   |
| svenska    | sv   |
| ελληνικά   | el   |
| polski     | pl   |
| русский    | ru   |

## multi-speaker diarization

on system audio, miniti uses deepgram's diarization to label remote speakers separately. you might see:

* **you** - your mic
* **speaker 1** - first remote voice
* **speaker 2** - second remote voice

diarization itself is source- and voice-based, not name-based. on top of it, miniti runs a separate inference pass that **does** try to resolve real names from the conversation (and from calendar attendees if connected) - so **speaker 1** will often turn into **jane** once there's enough signal. see [speaker names](/docs/features/speaker-names) and [google calendar](/docs/integrations/google-calendar).

## live transcript view

* text appears as deepgram returns interim results, then firms up when marked final
* smooth auto-scrolling keeps the newest content visible
* **selectable text** - the live and saved transcript, and insights, are fully selectable. drag to select on macos, long-press to select on ios, then copy any range without exporting the whole meeting
* search any meeting (including live sessions) - press `/` to focus the search field on macos

## what is sent where

in both **managed** and **byok** modes, audio streams directly from your device to deepgram over a websocket. miniti's backend is never in the audio path.

the difference is the key:

* **managed mode**: the backend issues a short-lived deepgram access token for each session. no deepgram account needed on your side. managed mode also stays connected more reliably on longer meetings and brief gaps.
* **byok mode**: the app uses your own deepgram key, stored locally in your keychain.

## troubleshooting

* **no transcript appears** - check microphone and (on macos) system audio permission, or check for error messages on the home screen
* **wrong language** - set the language before starting, not during
* **remote audio missing** - turn on system audio in the home screen and grant system audio recording permission
* **wrong product names** - add them to the [personal dictionary](#personal-dictionary) in settings
* **you and remote overlap on macos** - keep both mic and system audio on so each stays on its own channel

see [troubleshooting](/docs/reference/troubleshooting) for more.