aladac/chat
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: chatterbox TTS via madcat-tts daemon, Web Speech API STT, styled persona picker

Browse Source 
- tts.py: replace piper subprocess with HTTP POST to madcat-tts /v1/audio/speech (chatterbox voice cloning)
- chat.js: replace whisper server upload with browser Web Speech API (webkitSpeechRecognition)
- chat.css: style persona picker — appearance:none select, themed with CSS vars, mobile responsive
- main.py: default TTS voice → bt7274-en
This commit is contained in:
marauder-actual
2026-05-29 16:43:41 +02:00
parent f3c35eba72
commit ae384fe618
4 changed files with 165 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/main.py
+1 -1
View File
@@ -403,7 +403,7 @@ else:
# --- TTS / STT ---
TTS_ENABLED = os.environ.get("TTS_ENABLED", "true").lower() != "false"
TTS_VOICE = os.environ.get("TTS_VOICE", "en_US-amy-medium")
TTS_VOICE = os.environ.get("TTS_VOICE", "bt7274-en")
tts = TTS(voice=TTS_VOICE) if TTS_ENABLED else None
STT_ENABLED = os.environ.get("STT_ENABLED", "true").lower() != "false"