Video SDK useTranscription Hook - React Native

useTranscription Hook

useTranscription() takes the transcription callbacks and returns the methods that start and stop realtime transcription for the room.

useTranscription example

useTranscription react native hook

import { Constants, useTranscription } from "@videosdk.live/react-native-sdk";

function onTranscriptionStateChanged(data) {
  const { state } = data;

  if (state === Constants.transcriptionEvents.TRANSCRIPTION_STARTING) {
    console.log("Realtime Transcription is starting");
  } else if (state === Constants.transcriptionEvents.TRANSCRIPTION_STARTED) {
    console.log("Realtime Transcription is started");
  } else if (state === Constants.transcriptionEvents.TRANSCRIPTION_STOPPING) {
    console.log("Realtime Transcription is stopping");
  } else if (state === Constants.transcriptionEvents.TRANSCRIPTION_STOPPED) {
    console.log("Realtime Transcription is stopped");
  }
}

function onTranscriptionText(data) {
  let { participantName, text, timestamp } = data;
  console.log(`${participantName}: ${text} ${timestamp}`);
}

const { startTranscription, stopTranscription } = useTranscription({
  onTranscriptionStateChanged,
  onTranscriptionText,
});

Parameters

onTranscriptionStateChanged

• onTranscriptionStateChanged() will be triggered when the state of the realtime transcription changes.
• It receives { state }, where state is one of the Constants.transcriptionEvents values: TRANSCRIPTION_STARTING, TRANSCRIPTION_STARTED, TRANSCRIPTION_STOPPING or TRANSCRIPTION_STOPPED.
• The current state is also available as transcriptionState from useRoom().

---

onTranscriptionText

• onTranscriptionText() will be triggered whenever transcription text is available.
• It receives { participantId, participantName, text, timestamp, type }.
• participantId and participantName identify the speaker.
• timestamp is a string.
• type says whether the line is partial, which a later line for the same sentence replaces, or the settled sentence. It is null when not reported.

---

Returns

startTranscription()

• startTranscription() is used to start realtime transcription.

Parameters

config

• type : Object

• required : false

• This specifies the configurations for realtime transcription. You can specify following properties.

  • webhookUrl: VideoSDK calls this URL when the transcription state changes.
  • summary: Leave it out if you do not want a summary.
    • enabled: Indicates whether realtime transcription summary generation is enabled. Summary will be available after realtime transcription stopped.
    • prompt: provides guidelines or instructions for generating a custom summary based on the realtime transcription content.
  • modelConfig: Object, settings for the transcription model.

---

stopTranscription()

• stopTranscription() is used to stop realtime transcription.

---

Example

const { startTranscription, stopTranscription } = useTranscription();

const run = async () => {
  await startTranscription({
    webhookUrl: "https://www.example.com",
    summary: {
      enabled: true,
      prompt:
        "Write summary in sections like Title, Agenda, Speakers, Action Items, Outlines, Notes and Summary",
    },
  });

  await stopTranscription();
};

run();