- VoiceRegistry for trained voices from Kubeflow pipeline
- Custom voice routing in synthesize()
- NATS subjects for listing/refreshing voices
- pyproject.toml with ruff/pytest config
- Full test suite (26 tests)
- Gitea Actions CI (lint, test, docker, notify)
- Renovate config for automated dependency updates
Ref: ADR-0056, ADR-0057
- tts_streaming.py: NATS-based TTS using XTTS HTTP API
- Streaming audio chunks for low-latency playback
- Voice cloning support via reference audio
- Multi-language synthesis
- OpenTelemetry instrumentation with HyperDX support