fix(tts): clean streamed directive text

This commit is contained in:
Peter Steinberger
2026-04-26 04:08:03 +01:00
parent 2261918c8c
commit cf834e2a21
11 changed files with 290 additions and 17 deletions

View File

@@ -680,6 +680,10 @@ for a single reply, plus an optional `[[tts:text]]...[[/tts:text]]` block to
provide expressive tags (laughter, singing cues, etc) that should only appear in
the audio.
Streaming block delivery strips these directives from visible text before the
channel sees them, even when a directive is split across adjacent blocks. Final
mode still parses the accumulated raw reply for TTS synthesis.
`provider=...` directives are ignored unless `modelOverrides.allowProvider: true`.
Example reply payload: