I am getting this error. While trying to record the telephone call - TwirpError(code=invalid_argument, message=request has missing or invalid field: output, status=400)

Thanks for reaching out, Mridul. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

This is my code for it -

<http://logger.info|logger.info>("Starting recording the call") 
        lkapi = api.LiveKitAPI()  
          
        # Start room recording for the phone call  
        recording_request = api.RoomCompositeEgressRequest(  
            room_name=ctx.room.name,  
            layout="speaker",  
            preset=api.EncodingOptionsPreset.H264_720P_30,  
            audio_only=True,  
            file_outputs=[api.EncodedFileOutput(  
                filepath=f"recordings/{ctx.room.name}-{userdata.phone_number or 'unknown'}.mp4",  
                file_type=api.EncodedFileType.MP4,  
            )],  
        )  
          
        recording_info = await lkapi.egress.start_room_composite_egress(recording_request)  
        <http://logger.info|logger.info>(f"Started call recording: {recording_info}")  
          
        # Store recording info in userdata for cleanup  
        userdata.recording_info = recording_info  
        userdata.lkapi = lkapi

Hey there! I totally understand the frustration with this error. It looks like your recording setup is just missing a few key details. Think of it like trying to ship a package without a complete address – the system doesn't know exactly where to send your recording. I see you're using

file_outputs

, which is great! But it seems like we need to add a bit more information. If you're planning to save your recording to cloud storage like S3, Google Cloud Storage, or Azure Blob Storage, you'll want to include all those important credentials. Let me show you an example that might help: Sources: Session recording and transcripts | LiveKit Docs | Recording agent sessions | LiveKit Docs | GitHub::livekit::livekit_composite | livekit/livekit-cli/cmd/lk/egress.go

For poc I want to store it locally

Hey there! Thanks for sharing more about your local recording needs. I totally get wanting to keep things simple for your proof of concept. Storing the recording locally is super straightforward with the

file_outputs

field in your

RoomCompositeEgressRequest

. Check out this example I put together that should help you out:

recording_request = api.RoomCompositeEgressRequest(
    room_name=ctx.room.name,
    layout="speaker",
    preset=api.EncodingOptionsPreset.H264_720P_30,
    audio_only=True,
    file_outputs=[api.EncodedFileOutput(
        filepath=f"recordings/{ctx.room.name}-{userdata.phone_number or 'unknown'}.mp4",
        file_type=api.EncodedFileType.MP4,
    )],
)

Just a quick pro tip: make sure that

recordings/

directory is set up and ready to go. If you run into any hiccups, I'm right here to help you troubleshoot. We'll get this sorted out together!