Repository navigation
release/0.1: add scene3 and bump to 0.1.43 - #86
Merged
Merged
Conversation
scene3 speaks one text block, where inline [bracketed] cues such as [sighs] or [laughs] direct the delivery, and can clone one HTTP(S) reference recording. The audio block's meta.text may carry that recording's transcript; the request goes to /v1/audio/speech with the reference in metadata.references.
scene3 is used when the user or an external policy names it; the Qwen defaults are unchanged. The rejection tests already pin each message exactly, so the extra pattern check is dropped.
Release 0.1.43: adds the `scene3` text-to-speech model, with inline [bracketed] delivery cues and an optional one-reference clone whose transcript can ride on the audio block's meta.text. The qwen speech models are unchanged.
LingXuanYin
force-pushed
the
feat/scene3
branch
from
October 28, 2026 01:31
599e93a to
aabe5a4
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The 0.1 line, for dependents still on
^0.1.x: thescene3model and the 0.1.43 version, on a newrelease/0.1branch cut from the 0.1.42 release commit.These are the commits of #85 before its rebase onto main; main carries the same change on the 0.2 line. 0.1.43 is published under the dist-tag
release-0.1, solateststays on the 0.2 line.Evidence
2eb6d93, exported without line-ending conversion, in node:24-slim:pnpm lintchecks 72 files with no errors, typecheck passes, vitest 413 passed (19 files), build completes.scene3tests are the ones in feat: add the scene3 text-to-speech model #85.Merge Danger
Door: two-way for the code; a published version stays.
Blast Radius: none for existing callers; 0.1.43 only adds
scene3to 0.1.42.