PolyTalk CE 0.2.0

PolyTalk CE 0.2.0

This release adds Supertonic TTS support for Japanese and Korean, plus updated Docker/config examples and expanded documentation.

Highlights

• Added Supertonic TTS support for Japanese and Korean speech synthesis.
• Added language-based TTS provider routing so Japanese and Korean can use Supertonic while other languages continue using the default Piper path.
• Added Docker Compose support for the Supertonic TTS service, including a dedicated image build and persistent model/cache volume.
• Added Supertonic configuration examples in .env.example and config/config.yaml.example.
• Expanded README guidance for pipeline flow, use cases, provider compatibility, self-hosting, and benchmarking.
• Added tests for Supertonic routing, voice selection, synthesis requests, and provider-specific TTS behavior.

Validation

• pre-commit passed
• Python compile check passed
• Full test suite passed: 380 tests

PolyTalk CE 0.1.0

PolyTalk CE 0.1.0

Initial public Community Edition release baseline.

Highlights

• FastAPI application for self-hosted speech-to-speech live translation
• Browser UI with microphone capture and translated audio playback
• Mock mode for safe local testing without API keys
• Docker Compose setup with PolyTalk app, faster-whisper STT, and Piper TTS
• Configurable STT, translation, and TTS providers for self-hosted deployments

Validation

• pre-commit passed
• Full test suite passed: 377 tests