Skip to content

Add optional server frontend pipeline - #330

Open
0xShug0 wants to merge 1 commit into
mainfrom
server-frontend-module
Open

Add optional server frontend pipeline#330
0xShug0 wants to merge 1 commit into
mainfrom
server-frontend-module

Conversation

@0xShug0

@0xShug0 0xShug0 commented Aug 28, 2026

Copy link
Copy Markdown
Owner

Resolves #313

Summary

  • add an opt-in in-process server frontend pipeline with pre/post module hooks
  • add explicit module contracts for request and response envelope states
  • add audio_decode for MP3/FLAC ASR input via miniaudio
  • add mp3_encode for response_format=mp3 TTS output via libmp3lame
  • document how to add custom frontend modules

Validation

  • configured debug build with -DAUDIOCPP_BUILD_SERVER_FRONTENDS=ON -DAUDIOCPP_SERVER_FRONTEND_MODULES=audio_decode;mp3_encode
  • built build/debug/bin/audiocpp_server
  • validated MP3 ASR input returns expected text
  • validated FLAC ASR input returns expected text
  • validated TTS response_format=mp3 returns audio/mpeg and probes as MP3
  • ran git diff --check HEAD~1 HEAD

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.

[Feature Request / Bug]: Support non-WAV / browser audio uploads (WebM/Opus, MP3, OGG) on /v1/audio/transcriptions for Open WebUI compatibility

1 participant