Transcription

session.transcription turns what the user says into text. Register a handler and you start getting results; the SDK handles the subscription for you.

session.transcription.on((data) => {
  if (data.isFinal) {
    session.display.render([{type: "text", id: "msg", box: {x: 0, y: 0, w: 576, h: 288}, text: data.text}]);
  }
});

Transcription needs the MICROPHONE permission in your manifest. Without it, the phone rejects the subscription with PERMISSION_NOT_DECLARED and no events arrive.

Results

Each event is a TranscriptionData:

Field	Type	Notes
`text`	`string`	The transcribed text so far.
`isFinal`	`boolean`	`false` for interim results that keep updating, `true` once the utterance is settled.
`language`	`string?`	The detected language (when auto-detecting).

Interim results stream as the user speaks and get replaced; wait for isFinal if you only want settled text.

Targeting languages

on() auto-detects the language. To listen for specific ones, use forLanguage() with BCP-47 tags:

// One language.
session.transcription.forLanguage("en-US", (data) => { /* … */ });

// Several at once.
session.transcription.forLanguage(["en-US", "es-ES"], (data) => { /* … */ });

Each call is independent, and you can have several active at the same time.

Requiring on-device transcription

Pass {forceLocal: true} as the final argument to route that subscription through on-device STT and suppress cloud transcript delivery:

session.transcription.on(handler, {forceLocal: true});
session.transcription.forLanguage("en-US", handler, {forceLocal: true});

This requires a downloaded local STT model. Cloud transcripts are suppressed for the local-only subscription, even while other miniapps continue using cloud transcription. Routing is per listener, so a default listener on the same stream can continue receiving cloud transcription.

Configuring

configure() tunes the recognizer. It’s fire-and-forget and applies to subsequent results:

session.transcription.configure({
  languageHints: ["en", "ja"],     // ISO 639-1 hints to improve detection
  vocabulary: ["MentraOS", "HIPAA"], // boost domain terms
  diarization: true,                // tag speakers when the provider supports it
});

Cleaning up

Every subscription returns an unsubscribe function. stop() tears down every subscription this module owns at once:

const off = session.transcription.on(handler);
off();                       // drop this one

session.transcription.stop(); // drop all of them

session.transcription.hasPermission tells you whether MICROPHONE is declared in your manifest. It does not tell you whether the user granted the OS prompt: if they denied it, your handler simply never fires. See Permissions.

Transcription is for text. For raw audio frames or voice-activity detection, use session.mic. For translated text, use session.translation. Subscribing to one does not subscribe you to the others.

Getting Started

Core Concepts

UI Layer

Display

Audio & Speech

Sensors & Input

Camera

Phone & System

Data

Reference

Results

Targeting languages

Requiring on-device transcription

Configuring

Cleaning up

​Results

​Targeting languages

​Requiring on-device transcription

​Configuring

​Cleaning up

Results

Targeting languages

Requiring on-device transcription

Configuring

Cleaning up