To forward transcriptions to your backend in LiveKit, you can use the

STTSegmentsForwarder

class, which provides an interface for delivering transcriptions in real-time. Here are the best practices: • Set up the forwarder: Create an

STTSegmentsForwarder

instance with your room, participant, and track information. • Stream speech events: Use a speech stream from your STT provider and update the forwarder with speech events as they arrive. • Handle transcripts: Process both interim and final transcripts appropriately. For example, you can log them or send them to your backend. Here is a sample implementation:

from livekit.agents import stt, transcription
from livekit.plugins.deepgram import STT

async def _forward_transcription(
    stt_stream: stt.SpeechStream,
    stt_forwarder: transcription.STTSegmentsForwarder,
):
    """Forward the transcription and log the transcript in the console"""
    async for ev in stt_stream:
        stt_forwarder.update(ev)
        if ev.type == stt.SpeechEventType.INTERIM_TRANSCRIPT:
            print(ev.alternatives[0].text, end="")
        elif ev.type == stt.SpeechEventType.FINAL_TRANSCRIPT:
            print("\n")
            print(" -> ", ev.alternatives[0].text)

Let me know if you need further assistance or clarification! Sources: Tree View: | dse-workbench | Transcriptions | LiveKit Docs | Transcriptions | LiveKit Docs