|
|
372c6a5d3f
|
Add /v1/models endpoint for voice discovery
- Modified openedai.py to allow speech.py to define custom /v1/models
- Endpoint returns comprehensive model info including:
* All available voices per model
* Voice count
* Engine name (piper, xtts, silero, kokoro)
* Sample rate
* Description
- Supports all 4 TTS engines:
* tts-1 (Piper): 55 voices @ 22050 Hz
* tts-1-hd (XTTS): 8 voices @ 24000 Hz
* tts-1-silero (Silero): 148 voices @ 48000 Hz
* tts-1-kokoro (Kokoro): 34 voices @ 24000 Hz
This enables frontends to dynamically discover available voices
and their supported models without hardcoding voice lists.
🦝 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-09 13:51:59 -05:00 |
|
