- Refactor existing tests to use a shared mock engine fixture.
- Add tests for unsupported response formats.
- Add tests for engine synthesis failures.
- Add tests for 'engine:model_id' parsing in the 'model' parameter.
- Add tests for different audio response formats (opus, flac).
- Implements POST /v1/audio/speech endpoint (OpenAI API compatible).
- Integrates Kokoro and XTTS engines (including dependencies and implementations).
- Updates main application to register new engines and router.
- Adds unit tests for OpenAI compatibility.
- Updates requirements.txt for new engines.
