v0.0.23

Highlights

• Adds an OpenAI-compatible POST /v1/audio/speech endpoint to speech-server, supporting WAV and raw PCM output for drop-in local TTS integrations.
• Adds incremental Sortformer streaming, Nemotron emission-aligned word timestamps, and the ReDimNet2-B6 speaker identity encoder.
• Improves cached Whisper model startup.

What's Changed

• Optimize cached Whisper model loading by @ivan-digital in #410
• Add ReDimNet2-B6 speaker identity encoder by @ivan-digital in #409
• Add incremental Sortformer streaming session by @ivan-digital in #411
• docs: add public integration showcase and Homebrew stats by @ivan-digital in #412
• docs: remove zero-star adoption references by @ivan-digital in #413
• Expose emission-aligned word timestamps from Nemotron streaming by @ivan-digital in #414
• feat: add OpenAI-compatible speech synthesis by @ivan-digital in #415

Full Changelog: v0.0.22...v0.0.23