plugins: add Avaluma avatar plugin#6310
Open
Alpe6825 wants to merge 2 commits into
Open
Conversation
Add livekit-plugins-avaluma, a remote avatar integration for Avaluma (https://avaluma.ai), following the standard avatar plugin structure: DataStreamAudioOutput with publish_on_behalf and video-track waiting, plus agent/user turn-taking state forwarded to the avatar over RPC. - livekit-plugins/livekit-plugins-avaluma: the plugin - examples/avatar_agents/avaluma: example agent worker - livekit-agents: add the "avaluma" optional-dependency extra
|
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
Address review feedback: - wire the avatar audio via output.replace_audio_tail(...) like the other avatar plugins, preserving upstream chain wrappers (transcript sync, recording) instead of replacing the whole output chain - re-raise a non-retryable APIStatusError (e.g. 401/403) immediately instead of retrying and masking it with a generic APIConnectionError
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
livekit-plugins-avaluma, a remote avatar integration for Avaluma.Like the other avatar plugins, the agent's audio output is streamed to the Avaluma avatar worker via
DataStreamAudioOutput(withpublish_on_behalfand video-track waiting), and the avatar joins the room and streams video back. Agent and user turn-taking state changes are forwarded to the avatar over RPC.What's included
livekit-plugins/livekit-plugins-avaluma/— the plugin (PEP 420 namespace package,py.typed, Apache-2.0)examples/avatar_agents/avaluma/— example agent workerlivekit-agents:avalumaoptional-dependency extrapyproject.toml[tool.uv.sources]entry +uv.lockConfiguration
AVALUMA_LICENSE_KEY,AVALUMA_AVATAR_ID— requiredAVALUMA_AVATAR_SERVER_URL— optional, only when self-hosting the avatar serverChecks
ruff check✅ruff format --check✅mypy --strict✅Introduces the integration discussed in #6309. Happy to sign the CLA and coordinate versioning, the PyPI publish under the LiveKit org, and the docs page.