[inworld] Pre-open WebSocket TTS context on LLM response start#4013
Open
ianbbqzy wants to merge 1 commit intopipecat-ai:mainfrom
Open
[inworld] Pre-open WebSocket TTS context on LLM response start#4013ianbbqzy wants to merge 1 commit intopipecat-ai:mainfrom
ianbbqzy wants to merge 1 commit intopipecat-ai:mainfrom
Conversation
ianbbqzy
force-pushed
the
ian/prewarm-context-inworld-v2
branch
from
fa27151 to
dfe5fec
Compare
Codecov Report❌ Patch coverage is
... and 17 files with indirect coverage changes 🚀 New features to boost your workflow:
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
LLMFullResponseStartFramearrives, overlapping server-side context creation with sentence aggregation time_send_contextidempotent sorun_ttsskips the redundant create if the context was already prewarmedMotivation
Without prewarming, context creation happens inside
run_tts— after sentence aggregation completes — putting the server-side setup time on the TTFB critical path. By sending the context config as soon as the LLM turn starts, the server can allocate resources in parallel with text aggregation.Testing performed