RFC: Seedance audio stability for AIGC video skills#8
Closed
ZaynJarvis wants to merge 1 commit into
Closed
Conversation
ZaynJarvis
force-pushed
the
luna/seedance-audio-stability-rfc
branch
from
5209693 to
af8ffdb
Compare
Author
|
Closing this PR because the Seedance audio-stability RFC should be tracked as an issue in the Agentara skills repo, not submitted as a docs PR here. Reposted as agentara/skills#1. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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\n- add a draft RFC for Seedance/AI-video voice stability in Agentara skills\n- document current Agentara skill gap: video-plan/storyboard cover dialogue and sound design, but no reference-audio voice registry, preflight, or native-audio assembly contract\n- capture production lessons from the Dodo/Wangwang 45s Seedance native-audio run\n\n## Key RFC Points\n- voice locking requires reference_audio plus prompt-level speaker binding\n- two 15s reference tracks failed; practical total reference-audio limit is about <=15.2s\n- audio-reference mode should not mix with strict first/last-frame control\n- native audio validation must preserve generated segment audio during final concat\n- reference audio URLs must be durable and preflighted before generation\n\n## Validation\n- docs-only change\n- git diff --check passed