wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

NVIDIATTSService: process incoming audio frame right away

Browse Source 
Process audio as soon as we receive it from the generator. Previously, we were
reading from the generator and adding elements into a queue until there was no
more data, then we would process the queue.
This commit is contained in:
Aleix Conchillo Flaqué
2026-01-20 13:44:52 -08:00
parent 14495c425a
commit a787fd9cd8
2 changed files with 27 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3509.fixed.2.md Normal file
View File

@@ -0,0 +1 @@
- Optimized `NVIDIATTSService` to process incoming audio frames immediately.