We are using this in frontend to get the transcrip...
# ask-aid
dry-waiter-30582
06/24/2025, 6:27 PMWe are using this in frontend to get the transcription
Copy code
room.registerTextStreamHandler('lk.transcription', async (reader, participantInfo) => {
const message = await reader.readAll();
if (reader.info.attributes['lk.transcribed_track_id']) {
console.log(`New transcription from ${participantInfo.identity}: ${message}`);
} else {
console.log(`New message from ${participantInfo.identity}: ${message}`);
}
});t
tall-airline-16756
06/24/2025, 6:27 PMThanks for reaching out, Avadhootha. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
tall-airline-16756
06/24/2025, 6:27 PMThank you for sharing the code snippet and describing the issue. The behavior you're observing, where the agent's speech text is only received after the speech is completed, could be influenced by the configuration of the transcription system. Specifically, the following parameters might be relevant:
• max_delay: This controls the delay in seconds between the end of a spoken word and returning the final transcript results. The default value is 0.7 seconds.
• max_delay_mode: If set to
flexible