24/7 TikTok wizard runtime + Dockerfiles
Go to file
2026-07-08 19:47:16 +00:00
.github/workflows seed repo scaffold 2026-07-08 19:27:19 +00:00
persona voice reference text + Timmy persona 2026-07-08 19:37:45 +00:00
scripts voice reference text + Timmy persona 2026-07-08 19:37:45 +00:00
services tts: male VCTK fallback until voice-sample.wav lands 2026-07-08 19:41:02 +00:00
.env.example seed repo scaffold 2026-07-08 19:27:08 +00:00
docker-compose.yml seed repo scaffold 2026-07-08 19:27:07 +00:00
persona.yaml voice reference text + Timmy persona 2026-07-08 19:37:45 +00:00
persona.yaml.orig voice reference text + Timmy persona 2026-07-08 19:37:45 +00:00
persona.yaml.rej voice reference text + Timmy persona 2026-07-08 19:37:45 +00:00
portal.py portal: add live wizard web portal + websocket persona chat 2026-07-08 19:47:16 +00:00
README.md seed repo scaffold 2026-07-08 19:27:06 +00:00
requirements.txt portal: add live wizard web portal + websocket persona chat 2026-07-08 19:47:16 +00:00

live-wizard

24/7 live TikTok wizard. ponytail build: thin glue + best-in-class OSS + Dockerfiles.

run it

cp persona/voice-sample.wav persona/avatar.png .env # optional
docker compose up brain tts avatar-cpu router

persona

Edit persona/persona.yaml to change the wizard character without changing code.

services

  • brain: Ollama + model
  • tts: Coqui XTTS / F5-TTS with cloned voice
  • avatar-cpu: Wav2Lip on CPU for prototypes
  • router: audio loop + RTMP + TikTok Live connector