https://livekit.io logo
Join Slack
Powered by
When I am trying to setup egress, I am getting the...
# ask-ai
m
When I am trying to setup egress, I am getting the following error:
Copy code
livekit.api.twirp_client.TwirpError: TwirpError(code=invalid_argument, message=no supported codec is compatible with all outputs, status=400)
Here is my code:
Copy code
agent_req = lk_api.ParticipantEgressRequest(
        room_name=ctx.room.name,
        identity=agent_room_identity,
        screen_share=False,
        file_outputs=[
            lk_api.EncodedFileOutput(
                file_type=lk_api.EncodedFileType.OGG,
                filepath=file_path_agent,
                s3=lk_api.S3Upload(
                    # endpoint=S3_RECORDING_ENDPOINT,
                    bucket=S3_RECORDING_BUCKET_NAME,
                    region=S3_RECORDING_REGION,
                    access_key=S3_RECORDING_ACCESS_KEY,
                    secret=S3_RECORDING_SECRET_KEY,
                ),
            )
        ],
    )
    res = await lkapi.egress.start_participant_egress(agent_req)
What is the issue? I would prefer to use an audio-only format for the recording, so I do not want to switch to MP4
t
Thanks for reaching out, Daniel. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
It looks like this error happens because there isn’t an audio codec that works with all the outputs you’ve specified. For audio-only egress, here are a few friendly tips to help you out: • Try to use compatible output types. For instance, OGG uses Opus, while MP4 uses AAC. If the codecs don’t match, it can cause this error. • It’s best to avoid manually setting conflicting codecs. LiveKit is pretty smart and can usually pick the right codec for you automatically. • Stick to just one file output type. Having multiple outputs that need different codecs isn’t supported right now. • Make sure the formats you choose are supported and set up correctly. A good way to fix this would be to simplify your output configuration—maybe start with just one format like OGG—and double-check that all your settings match what the codec requires. If you run into any more questions or need a hand, please don’t hesitate to reach out. I’m here to help! Sources: Docs::Home | pkg/types/types_test.go | RoomComposite Egress | LiveKit Docs | Composite and web recordings | LiveKit Docs | livekit/livekit_egress.twirp.go
It looks like this error is happening because there isn’t an audio codec that works with all the outputs you’ve specified. Don’t worry, I’m here to help you get this sorted out! For audio-only egress, here are a few friendly tips: • Try to use output types that are compatible. For example, OGG uses Opus, while MP4 uses AAC. Mixing codecs that don’t match can cause this error. • It’s best not to set conflicting codecs manually. LiveKit does a great job selecting the right codec automatically for you. • Stick to just one file output type at a time. Having multiple file outputs that need different codecs isn’t supported and can lead to issues. • Make sure the formats you choose are supported and set up correctly. A good way to fix this is by simplifying your setup. Start with just one output type, like MP4, and then slowly add others while checking everything works smoothly. If you’d like to use OGG, just double-check that no other conflicting outputs are included.
m
But I am audio-only. Why doesn't OGG work? Where do I need to configure the output types?
t
I'd be happy to help you configure audio-only egress with OGG output! Just follow these simple steps: 1. Create a RoomCompositeEgressRequest: Make sure to set 
audio_only=True
and specify OGG as the file type in the 
file_outputs
configuration. Here's an example to guide you:
Copy code
from livekit import api

req = api.RoomCompositeEgressRequest(
    room_name="your-room-name",
    audio_only=True,
    file_outputs=[api.EncodedFileOutput(
        file_type=api.EncodedFileType.OGG,
        filepath="path/to/output.ogg",
        s3=api.S3Upload(
            bucket="your-bucket-name",
            region="your-region",
            access_key="your-access-key",
            secret="your-secret-key",
        ),
    )],
)
1. Configure the EncodedFileOutput: Double-check that 
file_type
is set to 
EncodedFileType.OGG
and the 
filepath
ends with 
.ogg
. Don’t forget to include your storage settings, like your S3 details. 2. Start the egress: Then, use the LiveKit API to kick off the recording process:
Copy code
lkapi = api.LiveKitAPI()
res = await lkapi.egress.start_room_composite_egress(req)
await lkapi.aclose()
Just so you know, OGG uses the Opus codec, which works perfectly for audio-only egress. If you run into any questions or need a hand with anything else, feel free to reach out—I’m here to help! Sources: Session recording and transcripts | LiveKit Docs | Session recording and transcripts | LiveKit Docs | livekit/livekit_egress.pb.go | pkg/config/output_file.go
m
I am already using 
audio_only=True
The problem is NOT 
RoomCompositeEgressRequest
it is 
ParticipantEgressRequest
. Here is the source code of 
ParticipantEgressRequest
:
Copy code
class ParticipantEgressRequest(_message.Message):
    __slots__ = ("room_name", "identity", "screen_share", "preset", "advanced", "file_outputs", "stream_outputs", "segment_outputs", "image_outputs", "webhooks")
    ROOM_NAME_FIELD_NUMBER: _ClassVar[int]
    IDENTITY_FIELD_NUMBER: _ClassVar[int]
    SCREEN_SHARE_FIELD_NUMBER: _ClassVar[int]
    PRESET_FIELD_NUMBER: _ClassVar[int]
    ADVANCED_FIELD_NUMBER: _ClassVar[int]
    FILE_OUTPUTS_FIELD_NUMBER: _ClassVar[int]
    STREAM_OUTPUTS_FIELD_NUMBER: _ClassVar[int]
    SEGMENT_OUTPUTS_FIELD_NUMBER: _ClassVar[int]
    IMAGE_OUTPUTS_FIELD_NUMBER: _ClassVar[int]
    WEBHOOKS_FIELD_NUMBER: _ClassVar[int]
    room_name: str
    identity: str
    screen_share: bool
    preset: EncodingOptionsPreset
    advanced: EncodingOptions
    file_outputs: _containers.RepeatedCompositeFieldContainer[EncodedFileOutput]
    stream_outputs: _containers.RepeatedCompositeFieldContainer[StreamOutput]
    segment_outputs: _containers.RepeatedCompositeFieldContainer[SegmentedFileOutput]
    image_outputs: _containers.RepeatedCompositeFieldContainer[ImageOutput]
    webhooks: _containers.RepeatedCompositeFieldContainer[_models.WebhookConfig]
    def __init__(self, room_name: _Optional[str] = ..., identity: _Optional[str] = ..., screen_share: bool = ..., preset: _Optional[_Union[EncodingOptionsPreset, str]] = ..., advanced: _Optional[_Union[EncodingOptions, _Mapping]] = ..., file_outputs: _Optional[_Iterable[_Union[EncodedFileOutput, _Mapping]]] = ..., stream_outputs: _Optional[_Iterable[_Union[StreamOutput, _Mapping]]] = ..., segment_outputs: _Optional[_Iterable[_Union[SegmentedFileOutput, _Mapping]]] = ..., image_outputs: _Optional[_Iterable[_Union[ImageOutput, _Mapping]]] = ..., webhooks: _Optional[_Iterable[_Union[_models.WebhookConfig, _Mapping]]] = ...) -> None: ...
if I just use RoomCompositeEgressRequest it works fine
t
Let's walk through how to configure 
ParticipantEgressRequest
for audio-only egress with OGG output together. Here’s a simple step-by-step guide: 1. Use 
EncodedFileOutput
with `file_type=OGG`: This will make sure your output is audio-only since OGG format supports audio perfectly. 2. Specify a file path and destination: You’ll want to set a 
filepath
that ends with 
.ogg
and also configure where to upload it (like an S3 bucket). 3. Optionally customize audio encoding: If you want to tweak audio details like bitrate or codec, you can use 
EncodingOptions
to get it just right. 4. Start the egress: Finally, use the SDK’s method to kick off the egress with your setup. Here’s an example in Python to help you visualize it:
Copy code
from livekit import api

file_output = api.EncodedFileOutput(
    file_type=api.EncodedFileType.OGG,
    filepath="recordings/audio-only.ogg",
    s3=api.S3Upload(
        bucket="your-bucket",
        region="your-region",
        access_key="your-access-key",
        secret="your-secret-key"
    ),
)

req = api.ParticipantEgressRequest(
    room_name="your-room",
    identity="participant-identity",
    file_outputs=[file_output]
)

lkapi = api.LiveKitAPI()
res = await lkapi.egress.start_participant_egress(req)
await lkapi.aclose()
Just a quick note: unlike 
RoomCompositeEgressRequest
, 
ParticipantEgressRequest
doesn’t have an 
audio_only
field. But by setting 
file_type=OGG
, you’re all set to record audio only. If anything feels unclear or you want to dive deeper, I’m here to help—just let me know!
Open in Slack
PreviousNext
Powered by