feat: TTS Stack - Chatterbox Multilingual + Whisper STT

- Chatterbox TTS Server (Multilingual, 23 Sprachen, Voice Cloning)
- Whisper STT Server (faster-whisper-small, CPU)
- RTX 4060 GPU auf Tdarr VM (node2, 10.2.1.104)
- Voice Profile: chantal.wav
- Chantal Telegram Voice Integration
This commit is contained in:
feldjaeger 2026-04-17 12:37:44 +02:00
commit 6115f3bc09
4 changed files with 167 additions and 0 deletions

37
compose.yaml Normal file
View file

@ -0,0 +1,37 @@
services:
chatterbox-tts:
build:
context: https://github.com/devnen/Chatterbox-TTS-Server.git
container_name: chatterbox-tts
restart: unless-stopped
ports:
- "8004:8004"
volumes:
- ./config.yaml:/app/config.yaml
- ./voices:/app/voices
- ./reference_audio:/app/reference_audio
- ./outputs:/app/outputs
- hf_cache:/app/hf_cache
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
whisper:
image: fedirz/faster-whisper-server:latest-cpu
container_name: whisper
restart: unless-stopped
ports:
- "8005:8000"
volumes:
- whisper-cache:/root/.cache/huggingface
environment:
- WHISPER__MODEL=Systran/faster-whisper-small
- WHISPER__DEVICE=cpu
volumes:
hf_cache:
whisper-cache: