Skip to content

docs(video): Seedance generate_audio defaults on for every input - #213

Merged
VickyXAI merged 1 commit into
mainfrom
docs/seedance-audio-on-by-default
Nov 11, 2026
Merged

VickyXAI merged 1 commit into
mainfrom
docs/seedance-audio-on-by-default

Conversation

@VickyXAI

Copy link
Copy Markdown
Contributor

Owner decision 2026-11-11: Seedance synced audio defaults ON for every input on all BlockRun gateways (server PRs in parallel). The blockrun_video tool told agents "Defaults ON for text-to-video and OFF for image/RealFace-conditioned".

  • generate_audio describe: "Seedance only: synced audio track. Default ON for every input; pass false for a silent clip." The moderation hint stays.
  • Tool description models header: "(on for every input)".

No code change: the tool only forwards generate_audio when the caller sets it. README and skills had no t2v-only wording.

Checks: npm run typecheck, npm run build, npm test (1479/1479). The schema token count for the full profile is still 14,265, so the README table and the card don't change.

Needs a release (version bump + npm publish) to reach users; none is done here.

🤖 Generated with Claude Code

The tool told agents audio was on for text-to-video and off for
image/RealFace-conditioned calls. The gateways now default it on for
every input; false gives a silent clip. Schema token count unchanged
(full profile 14,265).
@VickyXAI
VickyXAI merged commit b2264c0 into main Nov 11, 2026
3 checks passed
@VickyXAI
VickyXAI deleted the docs/seedance-audio-on-by-default branch November 11, 2026 22:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant