luke/ai-podcast
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add post-production pipeline: stem recorder, postprod script, recording UI

Browse Source 
New stem recording system captures 5 time-aligned WAV files (host, caller,
music, sfx, ads) during live shows. Standalone postprod.py processes stems
into broadcast-ready MP3 with gap removal, voice compression, music ducking,
and EBU R128 loudness normalization.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
tcpsyn
2026-02-08 17:53:32 -07:00
parent 356bf145b8
commit 7d88c76f90
12 changed files with 1528 additions and 363 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/services/tts.py
View File

@@ -598,7 +598,7 @@ async def generate_speech_inworld(text: str, voice_id: str) -> tuple[np.ndarray,
payload = {
"text": text,
"voice_id": voice,
"model_id": "inworld-tts-1.5-mini",
"model_id": "inworld-tts-1.5-max",
"audio_config": {
"encoding": "LINEAR16",
"sample_rate_hertz": 48000,