match python starter defaults and enable expressive mode - #60
Merged
Conversation
theomonnom
approved these changes
Aug 12, 2026
Port the Python starter's updated pipeline defaults to the Node starter: AssemblyAI Universal 3.5 Pro for STT (English), Fish Audio S2.1 Pro for TTS, and adaptive interruptions alongside the existing turn detector and preemptive generation. Enable expressive mode on the AgentSession, which injects the TTS provider's markup guide into the LLM prompt so the model emits inline delivery tags that Fish Audio renders and the transcript never shows. Requires @livekit/agents 1.6.3, which is now the dependency floor.
tinalenguyen
force-pushed
the
tina/expressive-update
branch
from
August 12, 2026 16:11
33c8ff1 to
14b31ec
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Enable expressive mode on the AgentSession, which injects the TTS provider's markup guide into the LLM prompt so the model emits inline delivery tags that Fish Audio renders and the transcript never shows. The flag ships in @livekit/agents 1.6.3 via livekit/agents-js#2267, so it carries a temporary @ts-expect-error to remove once that release is published.