Feat: Chatterbox-Klon-Referenz hochladen (eigene Stimme via ElevenLabs → lokal unbegrenzt klonen)

Browse Source

Sidecar: /reference (POST Upload → 24kHz-Mono-WAV via PyAV/faster-whisper, kein System-ffmpeg;
GET/DELETE). Chatterbox nutzt aktive Referenz (active.txt, überlebt Restart). Backend: /api/voice/
reference-Proxy. Picker (Chatterbox): „Referenz-Stimme hochladen (mp3/wav)" → setzt Stimme auf
»deine Referenz«. Ermöglicht den User-Plan: Stimme besorgen → EL erzeugen → Chatterbox klont.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

...

This commit is contained in:

Hitonabi

2026-06-28 00:55:40 +02:00

parent 75727c6b36

commit eeb397f066

6 changed files with 304 additions and 159 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

frontend/dist/assets/index-Dtig7Izl.js

Vendored

+5454

File diff suppressed because one or more lines are too long