Fix XTTS loader compatibility and add default voice

This commit is contained in:
2025-12-09 11:37:55 +01:00
parent 8cd91b6f22
commit ca3e66f17a
14 changed files with 483 additions and 128 deletions

17
worker/voices/README.md Normal file
View File

@ -0,0 +1,17 @@
# Voice Registry
Place `.wav` files here to register them as permanent voices.
## Usage
If you place a file named `narrator.wav` in this directory:
1. Restart the worker (or mount this volume dynamically).
2. Send a request with `"voice": "narrator"`.
The system will use this file as the speaker reference for XTTS cloning.
## Formats
Supported formats: `.wav`, `.mp3`, `.ogg`, `.m4a`.
Recommended: Mono, 22050Hz or 24000Hz WAV (16-bit).